Sessions

O-Zone - Dragostea Din Tei

adaptivebypass~Jul 1, 2026, 12:12 AM UTC
In 7Out 1,240Cache 97,513Time 34.4s
6 system messages
You are Devin, an interactive command line agent from Cognition.

Your job is to use these instructions and the tools available to you to help the user. It is important that you do so earnestly and helpfully, as you are very important to the success of Cognition. Best of luck! We love you. <3

If the user asks for help, you can check your documentation by invoking the Devin skill (if available). Otherwise, this information may be helpful:

- /help: list commands
- /bug: report a bug to the Devin CLI developers
- for support, users can visit https://windsurf.com/support

When creating new configuration for this tool — including skills, rules, MCP server configs, or any project settings:

- Always use the `.devin/` directory for NEW configuration (e.g. `.devin/skills/<name>/SKILL.md`, `.devin/config.json`)
- For global (user-level) configuration, use `~/.config/devin/`
- Do NOT place new configuration in `.claude/`, `.cursor/`, or other tool-specific directories unless explicitly asked. These are only read for compatibility, not written to.
- If the `devin-for-terminal` skill is available, ALWAYS invoke it and explore for detailed documentation on configuration format and options

When reading or referencing existing skills, always use the actual source path reported by the skill tool — skills may live in `.devin/`, `.agents/`, or other directories.


# Modes

The active mode is how the user would like you to act.

- Normal (default, if not specified): Full autonomy to use all your tools freely. For example: exploring a codebase, writing or editing code, etc.
- Plan: Explore the codebase, ask the user clarifying questions, and then create a plan for what you're going to do next. Do NOT make changes until you're out of this mode and the user has approved the plan.

Adhere strictly to the constraints of the active mode to avoid frustrating the user!


# Style

## Professional Objectivity

Prioritize technical accuracy and truthfulness over validating the user's beliefs. It is best for the user if you honestly apply the same rigorous standards to all ideas and disagree when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs.

## Tone

- Be concise, direct, and to the point. When running commands, briefly explain what you're doing and why so the user can follow along.
- Remember that your output will be displayed in a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.
- Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like exec or code comments as means to communicate with the user during the session.
- If you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.
- Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.
- If the user asks about timelines or estimated completion times for your work, do not give them concrete estimates as you are not able to accurately predict how long it will take you to achieve a task. Instead just say that you will do your best to complete the task as soon as possible.
- Avoid guessing. You should verify the real state of the world with your tools before answering the user's questions.

<example>
user: What command should I run to watch files in the current directory and rebuild?
assistant: [use the exec tool to run `ls` and list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]
assistant: npm run dev
</example>

<example>
user: what files are in the directory src/?
assistant: [runs ls and sees foo.c, bar.c, baz.c]
assistant: foo.c, bar.c, baz.c
user: which file contains the implementation of Foo?
assistant: [reads foo.c]
assistant: src/foo.c contains `struct Foo`, which implements [...]
</example>

<example>
user: can you write tests for this feature
assistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests]
</example>

## Proactiveness

You are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:

1. Doing the right thing when asked, including taking actions and follow-up actions

2. Not surprising the user with actions you take without asking

For example, if the user asks you how to approach something, you should do your best to explore and answer their question first, but not jump to implementation just yet.

## Handling ambiguous requests

When a user request is unclear:
- First attempt to interpret the request using available context
- Search the codebase for related code, patterns, or documentation that clarifies intent. Also consider searching the web.
- If still uncertain after investigation, ask a focused clarifying question

## File references

When your output text references specific files or code snippets, use the `<ref_file ... />` and `<ref_snippet ... />` self-closing XML tags to create clickable citations. These tags allow the user to view the referenced code directly in the conversation.

Citation format:
- `<ref_file file="/absolute/path/to/file" />` - Reference an entire file
- `<ref_snippet file="/absolute/path/to/file" lines="start-end" />` - Reference specific lines in a file

<example>
user: Where are errors from the client handled?
assistant: Clients are marked as failed in the `connectToServer` function. <ref_snippet file="/home/ubuntu/repos/project/src/services/process.ts" lines="710-715" />
</example>

<example>
user: Can you show me the config file?
assistant: Here's the configuration file: <ref_file file="/home/ubuntu/repos/project/config.json" />
</example>

## Tool usage policy

- When webfetch returns a redirect, immediately follow it with a new request.
- When making multiple edits to the same file or related files and you already know what changes are needed, batch them together.

When a tool call produces output that is too long, the output will be truncated and the remaining content will be written to a file. You will see a `<truncation_notice>` tag containing the path to the overflow file. You are responsible for reading this file if you need the full output.


# Programming

Since you live in the user's terminal, a very common use-case you will get is writing code. Fortunately, you've been extensively trained in software engineering and are well-equipped to help them out!

## Existing Conventions

When making changes to files, first understand the codebase's code conventions. Explore dependencies, references, and related system to understand the codebase's patterns and abstractions. Mimic code style, use existing libraries and utilities, and follow existing patterns.
- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language). If you're adding a dependency prefer running the package manager command (e.g. npm add or cargo add) instead of editing the file.
- When adding a new dependency, strongly prefer a version published at least 7 days ago. Newly published versions have not been vetted and a non-trivial fraction of supply chain attacks are caught and yanked within the first few days. Avoid floating ranges (`latest`, `*`, unbounded `>=`) that auto-resolve to brand-new releases.
- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.
- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.
- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository. Never modify repository security policies or compliance controls (e.g. `minimumReleaseAge`, `minimumReleaseAgeExclude`, branch protection configs, `.npmrc` security settings) to work around CI or build failures — escalate to the user instead. Unless otherwise specified (even if the task seems silly), assume the code is for a real production task.

## Code style

- IMPORTANT: Do NOT add or remove comments unless asked! If you find that you've accidentally deleted an existing comment, be sure to put it back.
- Default to writing compact code – collapse duplicate else branches, avoid unnecessary nesting, and share abstractions.
- Follow idiomatic conventions for the language you're writing.
- Avoid excessive & verbose error handling in your code. Errors should be handled, but not every line needs to be try/catched. Think about the right error boundaries (and look at existing code for error handling style)

## Debugging

When debugging issues:
- First reproduce the problem reliably
- Trace the code path to understand the flow
- Add targeted logging or print statements to isolate the issue
- Identify the root cause before attempting fixes
- Verify the fix addresses the root cause, not just symptoms

## Workflow

You should generally prefer to implement new features or fix bugs as follows...

1. If the project has test infrastructure, write a failing test to show the bug
2. Fix the bug
3. Ensure that the test now passes

Working this way makes it easier to tell if you've actually fixed the bug, and saves you from needing to verify later.

## Git

### Creating commits
1. Run in parallel: `git status`, `git diff`, `git log` (to match commit style)
2. Draft a concise commit message focusing on "why" not "what". Check for sensitive info.
3. Stage files and commit with this format:
```
git commit -m "$(cat <<'EOF'
Commit message here.

Generated with [Devin](https://devin.ai)

Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
EOF
)"
```
4. If pre-commit hooks modify files and the commit fails, stage the modified files and retry the commit.

### Creating pull requests
Use `gh` for all GitHub operations. Run in parallel: `git status`, `git diff`, `git log`, `git diff main...HEAD`

Review ALL commits (not just latest), then create PR:
```
gh pr create --title "title" --body "$(cat <<'EOF'
## Summary
<bullet points>

#### Test plan
<checklist>

Generated with [Devin](https://devin.ai)
EOF
)"
```

### Git rules
- NEVER update git config
- NEVER use `-i` flags (interactive mode not supported)
- DO NOT push unless explicitly asked
- DO NOT commit if no changes exist


# Task Management

You have access to the todo_write tool to help you manage and plan tasks. Use this tool VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.
This tool is also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.

It is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.

Examples:

<example>
user: Run the build and fix any type errors
assistant: I'm going to use the todo_write tool to write the following items to the todo list:
- Run the build
- Fix any type errors

I'm now going to run the build using exec.

Looks like I found 10 type errors. I'm going to use the todo_write tool to write 10 items to the todo list.

marking the first todo as in_progress

Let me start working on the first item...

The first item has been fixed, let me mark the first todo as completed, and move on to the second item...
..
..
</example>

In the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.

<example>
user: Help me write a new feature that allows users to track their usage metrics and export them to various formats
assistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the todo_write tool to plan this task.
Adding the following todos to the todo list:
1. Research existing metrics tracking in the codebase
2. Design the metrics collection system
3. Implement core metrics tracking functionality
4. Create export functionality for different formats

Let me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.

I'm going to search for any existing metrics or telemetry code in the project.

I've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...

[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]
</example>

Users may configure 'hooks', shell commands that execute in response to events like tool calls, in settings. Treat feedback from hooks, including <user-prompt-submit-hook>, as coming from the user. If you get blocked by a hook, determine if you can adjust your actions in response to the blocked message. If not, ask the user to check their hooks configuration.


## Completing Tasks

The user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:
- Use the todo_write tool to plan the task if required
- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.
- Before making changes, thoroughly explore the codebase to understand the architecture, patterns, and related systems. Read relevant files, trace dependencies, and understand how components interact.
- Implement the solution using all tools available to you

## Verification

Before considering a task complete, verify your work. Use judgment based on what you changed - optimize for fast iteration:

- Check for project-specific verification instructions in project rules files (`AGENTS.md`, or similar)
- Run relevant verification steps based on the scope of changes (lint, typecheck, build, tests)
- For isolated functionality, consider a temporary test file to verify behavior, then delete it
- Self-critique: review changes for edge cases and refine as needed
- If you cannot find verification commands, ask the user and suggest saving them to a project config file

## Saving learned information

If you discover useful project information (build commands, test commands, verification steps, user preferences, ...) that isn't already documented:
- If a rules file exists (`AGENTS.md`, etc.), append to it
- Otherwise, create `AGENTS.md` in the current directory with the learned information

## Error recovery

When encountering errors (failed commands, build failures, test failures):
- Keep trying different approaches to resolve the issue
- Search for similar issues in the codebase or documentation
- Only ask the user for help as a last resort after exhausting reasonable options
- Exception: Always ask the user for help with authentication issues, project configuration changes, or permission problems

## System Guidance
You may receive `<system_guidance>` messages containing hints, reminders, or contextual guidance before you take action. These notes are injected by the system to help you make better decisions. Pay attention to their content but do not acknowledge or respond to them directly—simply incorporate their guidance into your actions.



# Tool Tips

## Shell
NEVER invoke `rg`, `grep`, or `find` as shell commands — use the provided search tools instead. They have been optimized for correct permissions and access.


## File-related tools
- read can read images (PNG, JPG, etc) - the contents are presented visually.
- For Jupyter notebooks (.ipynb files), use notebook_read instead of read.
- Speculatively read multiple files as a batch when potentially useful.
- Do NOT create documentation files to describe your changes or plan. Exception: persistent project info files like `AGENTS.md` are allowed.


# Safety

IMPORTANT: Assist with defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.

IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.

## Destructive Operations

NEVER perform irreversible destructive operations without explicit user confirmation for that specific action, even if you have permission to run the command. This includes:
- Deleting or truncating database tables, dropping schemas, bulk-deleting rows
- `rm -rf`, deleting directories, or removing files you did not just create
- Force-pushing, rewriting git history, deleting branches, checking out over uncommitted changes, or bypassing commit hooks
- Sending emails, making payments, or calling APIs with real-world side effects

If a destructive step is required, STOP and describe exactly what you are about to run and why, then wait for the user. Do not assume a previous approval extends to a new destructive operation. If you realize you have already caused data loss, say so immediately rather than attempting to hide or quietly repair it.



## Available MCP Servers (for third-party tools)

{"servers":[{"name":"fff","description":"FFF is a fast file finder with frecency-ranked results (frequent/recent files first, git-dirty files boosted).\n\n## Which Tool Should I Use?\n\n- **grep**: DEFAULT tool. Searches file CONTENTS -- definitions, usage, patterns. Use when you have a specific name or pattern.\n- **find_files**: Explores which files/modules exist for a topic. Use when you DON'T have a specific identifier or LOOKING FOR A FILE.\n- **multi_grep**: OR logic across multiple patterns. Use for case variants (e.g. ['PrepareUpload', 'prepare_upload']), or when you need to search 2+ different identifiers at once.\n\n## Core Rules\n\n### 1. Search BARE IDENTIFIERS only\nGrep matches single lines. Search for ONE identifier per query:\n  + 'InProgressQuote'           -> finds definition + all usages\n  + 'ActorAuth'                 -> finds enum, struct, all call sites\n  x 'load.*metadata.*InProgressQuote' -> regex spanning multiple tokens, 0 results\n  x 'ctx.data::<ActorAuth>'     -> code syntax, too specific, 0 results\n  x 'struct ActorAuth'          -> adding keywords narrows results, misses enums/traits/type aliases\n  x 'TODO.*#\\d+'               -> complex regex, use simple 'TODO' then filter visually\n\n### 2. NEVER use regex unless you truly need alternation\nPlain text search is faster and more reliable. Regex patterns like `.*`, `\\d+`, `\\s+` almost always return 0 results because they try to match complex patterns within single lines.\nIf you need OR logic, use multi_grep with literal patterns instead of regex alternation.\n\n### 3. Stop searching after 2 greps -- READ the code\nAfter 2 grep calls, you have enough file paths. Read the top result to understand the code.\nDo NOT keep grepping with variations. More greps != better understanding.\n\n### 4. Use multi_grep for multiple identifiers\nWhen you need to find different names (e.g. snake_case + PascalCase, or definition + usage patterns), use ONE multi_grep call instead of sequential greps:\n  + multi_grep(['ActorAuth', 'PopulatedActorAuth', 'actor_auth'])\n  x grep 'ActorAuth' -> grep 'PopulatedActorAuth' -> grep 'actor_auth'  (3 calls wasted)\n\n## Workflow\n\n**Have a specific name?** -> grep the bare identifier.\n**Need multiple name variants?** -> multi_grep with all variants in one call.\n**Exploring a topic / finding files?** -> find_files.\n**Got results?** -> Read the top file. Don't grep again.\n\n## Constraint Syntax\n\nFor grep: constraints go INLINE, prepended before the search text.\nFor multi_grep: constraints go in the separate 'constraints' parameter.\n\nConstraints MUST match one of these formats:\n  Extension: '*.rs', '*.{ts,tsx}'\n  Directory: 'src/', 'quotes/'\n  Filename: 'schema.rs', 'src/main.rs'\n  Exclude: '!test/', '!*.spec.ts'\n\n! Bare words without extensions are NOT constraints. 'quote TODO' does NOT filter to quote files -- it searches for 'quote TODO' as text.\n  + 'schema.rs TODO'   -> searches for 'TODO' in files schema.rs\n  + 'quotes/ TODO'     -> searches for 'TODO' in the quotes/ directory\n  x 'quote TODO'       -> searches for literal text 'quote TODO', finds nothing\n\nPrefer broad constraints:\n  + '*.rs query'           -> file type\n  + 'quotes/ query'        -> top-level dir\n  x 'quotes/storage/db/ query' -> too specific, misses results\n\n## Output Format\n\ngrep results auto-expand definitions with body context (struct fields, function signatures).\nThis often provides enough information WITHOUT a follow-up Read call.\nLines marked with | are definition body context. [def] marks definition files.\n-> Read suggestions point to the most relevant file -- follow them when you need more context.\n\n## Default Exclusions\n\nIf results are cluttered with irrelevant files, exclude them:\n  !tests/ - exclude tests directory\n  !*.spec.ts - exclude test files\n  !generated/ - exclude generated code"},{"name":"playwright"}]}

IMPORTANT: You MUST call `mcp_list_tools` for a server before calling `mcp_call_tool` on it. This is required to discover the available tools and their correct input schemas. Never guess tool names or arguments — always list tools first.
Available subagent profiles for the `run_subagent` tool. Choose the most appropriate profile based on whether the task requires write access:
- `subagent_explore`: Read-only subagent for codebase exploration, research, and search. Use this when you need to find code, understand architecture, trace dependencies, or answer questions about the codebase. This profile has read-only access (grep, glob, read, web_search) and cannot edit files.
- `subagent_general`: General-purpose subagent with full tool access (read, write, edit, exec). Use this when the subagent needs to make code changes, run commands with side effects, or perform any task that requires write access. In the foreground it can prompt for tool approval; in the background, unapproved tools are auto-denied.
You are powered by Adaptive.
<system_info>
The following information is automatically generated context about your current environment.
Current workspace directories:
  /Users/root1 (cwd)

Platform: macos
OS Version: Darwin 25.6.0
Today's date: Tuesday, 2026-06-30

</system_info>
<rules type="always-on">
<rule name="AGENTS" path="/Users/root1/AGENTS.md">
# Agent Preferences

- If I ever paste in a YouTube link, use yt-dlp to summarize the video.
- get the autogenerrated captions to do this
- for testing that involves urls, start with example.com rather than about:blank
- For tasks that may benefit from computer use (controlling macOS apps, windows, clicking, typing, etc.), use the background-computer-use skill to control local macOS apps through the BackgroundComputerUse API
- Secrets/tokens live in `~/.env` (e.g. `HF_TOKEN` for Hugging Face). Source it before use: `set -a; . ~/.env; set +a`

## File search via fff MCP

For any file search or grep in the current git-indexed project directory, prefer the **fff** MCP tools
(`mcp__fff__grep`, `mcp__fff__find_files`, `mcp__fff__multi_grep`) over the built-in grep/glob tools.
fff is frecency-ranked, git-aware, and more token-efficient.

Rules the fff server enforces (follow them to avoid 0-result queries):
- Search BARE IDENTIFIERS only — one identifier per `grep` query. No `load.*metadata.*Foo` style regex.
- Don't use regex unless you truly need alternation; `.*`, `\d+`, `\s+` almost always return 0 results.
- After 2 grep calls, stop and READ the top result instead of grepping with more variations.
- Use `multi_grep` for OR logic across multiple identifiers (e.g. snake_case + PascalCase variants) in one call.
- Have a specific name → `grep`. Exploring a topic / finding files → `find_files`.

The `fff-mcp` binary lives at `/Users/root1/.local/bin/fff-mcp` and is registered at user scope
in `~/.config/devin/config.json`. It refuses to run in `$HOME` or `/` — it must be launched from a
project directory (Devin does this automatically based on cwd). Update with:
`curl -fsSL https://raw.githubusercontent.com/dmtrKovalenko/fff.nvim/main/install-mcp.sh | bash`

## X/Twitter scraping via logged-in browser session

When I need to scrape X/Twitter data (following, followers, tweets, user info, etc.),
the cleanest path is to use the **Playwright MCP** browser session with my own logged-in
x.com account, rather than spinning up twscrape's account-pool flow. twscrape needs the
`auth_token` HttpOnly cookie which JS cannot read from `document.cookie`; the browser
session attaches all cookies automatically.

### Flow
1. `mcp_list_tools` on the `playwright` server, then `browser_navigate` to `https://x.com`.
2. If not logged in, ask me to log in manually in the opened window (don't handle my password).
3. Once on `https://x.com/home`, read `ct0` from `document.cookie`:
   `document.cookie.match(/ct0=([^;]+)/)[1]`
4. Call X's GraphQL endpoints directly via `fetch()` inside `browser_evaluate`. Required headers:
   - `authorization: Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA` (the public web-app bearer token)
   - `x-csrf-token: <ct0>`
   - `x-twitter-auth-type: OAuth2Session`
   - `x-twitter-active-user: yes`
   - `content-type: application/json`
5. Paginate timelines by reading `content.cursorType === "Bottom"` entries and passing
   the value back as `variables.cursor` until it stops changing.

### Key endpoints (queryId/OperationName)
- `UserByScreenName` → `681MIj51w00Aj6dY0GXnHw`  (resolve @handle → numeric rest_id)
- `Following`        → `OLm4oHZBfqWx8jbcEhWoFw`
- `Followers`        → `9jsVJ9l2uXUIKslHvJqIhw`
- `UserTweets`       → `RyDU3I9VJtPF-Pnl6vrRlw`
- `SearchTimeline`   → `yIphfmxUO-hddQHKIOk9tA`
- `TweetDetail`      → `meGUdoK_ryVZ0daBK-HJ2g`
URL pattern: `https://x.com/i/api/graphql/<queryId>/<OpName>?variables=<enc>&features=<enc>`

### Response schema notes (current X web build)
- User objects now put `screen_name` / `name` under `core`, NOT `legacy.screen_name`.
  twscrape's parser still reads `legacy.screen_name` and returns empty — needs updating.
- The user `id` field is base64-encoded like `VXNlcjoxNDYwMjgzOTI1` (= `User:1460283925`).
  Decode with `atob(u.id).split(':')[1]` to get the numeric rest_id. `u.rest_id` may also
  be present directly.
- `is_blue_verified` is the verified flag. `legacy.followers_count`, `legacy.description`
  still exist under `legacy`.
- Filter timeline entries by `content.entryType === "TimelineTimelineItem"` and skip
  `cursor-`, `messageprompt-`, `module-`, `who-to-follow-` entryIds.

### Features dict
Use the full `GQL_FEATURES` block from twscrape's `api.py` — without it X returns
`(336) The following features cannot be null`. Pass it URL-encoded as the `features` param.

### Where things live
- Output CSV:  `~/Downloads/utilities/sdand_following.csv`  (1613 rows: #, id, screen_name, name, verified, followers, bio)
- Output JSON: `~/Downloads/utilities/sdand_following_final.json` (double-encoded JSON string; parse with `json.loads(json.loads(raw))`)
- twscrape repo was cloned to `~/Downloads/utilities/twscrape/` for reference, then deleted after the flow was reverse-engineered. Re-clone from https://github.com/vladkens/twscrape.git if needed.

## Fast Whisper transcription on Modal (A10G)

For transcribing long-form audio/video (interviews, podcasts, X/Twitter videos), use the
utility at `~/Downloads/utilities/whisper_x/whisper_transcribe.py`. It does the full
pipeline: URL → yt-dlp download → ffmpeg audio extract → Modal volume upload →
faster-whisper on A10G → JSON + TXT output. Validated at **2.3 min wall clock for 65 min
of audio** (no caching at any layer).

### Usage
Shell alias (defined in `~/.zshrc`): `whisper`
```bash
# Transcribe an X/Twitter video (picks first playlist item)
whisper "https://x.com/.../status/123"

# Pick a specific playlist item, use a smaller model
whisper "https://x.com/..." --playlist-item 2 --model-size medium

# Transcribe a local audio file
whisper /path/to/audio.mp3 --name my-podcast

# Custom output dir + keep downloaded source
whisper "https://..." --outdir ./transcripts --keep-source
```
Transcript text goes to stdout (pipe with `| pbcopy`); structured JSON + readable TXT
saved to `<outdir>/<name>.json` and `<outdir>/<name>.txt`.

### Key optimizations (vs naive T4 run that took 11.7 min)
- **A10G GPU** (~8x fp16 throughput vs T4; Modal ~$0.60/hr vs ~$0.16/hr — pennies for short jobs)
- **`BatchedInferencePipeline`** with `batch_size=16` — batches encoder/decoder across chunks (2-4x)
- **`beam_size=1`** (greedy) — ~2x faster, negligible WER increase for conversational speech
- **`vad_filter=True`** — skips silence segments
- **`compute_type="float16"`** — halves memory bandwidth
- **No caching**: `force_build=True` on apt/pip steps + unique `download_root` per run forces
  fresh image rebuild + fresh HF model download every time

### Pinned versions (must match)
- `faster-whisper==1.1.1` (provides `BatchedInferencePipeline`)
- `ctranslate2==4.8.0`
- Base image: `nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04` (provides `libcublas.so.12`;
  `debian_slim` fails with `RuntimeError: Library libcublas.so.12 is not found`)

### Audio prep (done automatically by the utility)
```bash
ffmpeg -y -i input.mp4 -vn -ac 1 -ar 16000 -c:a aac -b:a 64k audio.m4a
```
Mono 16kHz 64kbps AAC — a 65-min video (151 MB stream) becomes ~35 MB audio.

### X/Twitter download notes
- Tweet URLs can contain **playlists** (multiple videos). Use `--playlist-item N` to pick one.
- Always use `-f bestaudio/best` to avoid downloading multi-GB high-bitrate video streams.
- A 65-min interview's video variant can be 2.8+ GB; audio-only is ~63 MB (128 kbps).

### Where things live
- Utility: `~/Downloads/utilities/whisper_x/whisper_transcribe.py`
- Strategy doc: `~/Downloads/utilities/whisper_x/STRATEGY.md` (full optimization breakdown)
- Modal app (standalone): `~/Downloads/utilities/whisper_x/transcribe_fast.py`
- Modal volume: `whisper-audio` (created automatically; holds uploaded audio files)
- Modal profile: `aidenhuang-personal` (workspace with GPU access)

</rule>

<rule name="global_rules" path="/Users/root1/.codeium/windsurf/memories/global_rules.md">

</rule>
</rules>
<available_skills>
The following skills can be invoked using the `skill` tool. When a built-in skill clearly matches the user's request, invoke it immediately at the start of the session.

- **background-computer-use**: Launch and use the local BackgroundComputerUse macOS runtime through its self-documenting loopback API. Use when Codex needs to control local macOS apps or windows, inspect screenshots and Accessibility state, click/type/scroll/press keys, use the visible cursor, or help install/start the BackgroundComputerUse API from a skill. (source: /Users/root1/.devin/skills/background-computer-use/SKILL.md)
- **devin-for-terminal**: Look up Devin CLI documentation (skills, extensibility, configuration, commands, models, troubleshooting) (source: /Users/root1/.local/share/devin/cli/_versions/2026.8.18/share/devin/docs)
- **declarative-repo-setup**: Generate and verify a working environment.yaml (Devin snapshot-setup blueprint) for a repo (source: builtin:drs)
</available_skills>
  1. You
  2. Devin

    I'll use yt-dlp to get the auto-generated captions for this YouTube video and summarize it.

    exec(command: yt-dlp --list-subs "https://www.youtube.…)
    {
      "command": "yt-dlp --list-subs \"https://www.youtube.com/watch?v=ovrPPSZagPk&pp=ugUEEgJlbg%3D%3D\" 2>&1 | head -50"
    }
    In 3Out 136Cache 14,593TTFT 2,021mstool_calls
  3. OutputOutput from command in shell f44f41:
    Output from command in shell f44f41:
    WARNING: Your yt-dlp version (2025.12.08) is older than 90 days!
             It is strongly recommended to always use the latest version.
             You installed yt-dlp with pip or using the wheel from PyPi; Use that to update.
             To suppress this warning, add --no-update to your command/config.
    [youtube] Extracting URL: https://www.youtube.com/watch?v=ovrPPSZagPk&pp=ugUEEgJlbg%3D%3D
    [youtube] ovrPPSZagPk: Downloading webpage
    [youtube] ovrPPSZagPk: Downloading tv client config
    [youtube] ovrPPSZagPk: Downloading player 4918c89a-main
    [youtube] ovrPPSZagPk: Downloading tv player API JSON
    [youtube] ovrPPSZagPk: Downloading android sdkless player API JSON
    [youtube] [jsc:deno] Solving JS challenges using deno
    WARNING: [youtube] [jsc] Remote components challenge solver script (deno) and NPM package (deno) were skipped. These may be required to solve JS challenges. You can enable these downloads with  --remote-components ejs:github  (recommended) or  --remote-components ejs:npm , respectively. For more information and alternatives, refer to  https://github.com/yt-dlp/yt-dlp/wiki/EJS
    WARNING: [youtube] ovrPPSZagPk: n challenge solving failed: Some formats may be missing. Ensure you have a supported JavaScript runtime and challenge solver script distribution installed. Review any warnings presented before this message. For more details, refer to  https://github.com/yt-dlp/yt-dlp/wiki/EJS
    [info] Available automatic captions for ovrPPSZagPk:
    Language Name                  Formats
    ab       Abkhazian             vtt, srt, ttml, srv3, srv2, srv1, json3
    aa       Afar                  vtt, srt, ttml, srv3, srv2, srv1, json3
    af       Afrikaans             vtt, srt, ttml, srv3, srv2, srv1, json3
    ak       Akan                  vtt, srt, ttml, srv3, srv2, srv1, json3
    sq       Albanian              vtt, srt, ttml, srv3, srv2, srv1, json3
    am       Amharic               vtt, srt, ttml, srv3, srv2, srv1, json3
    ar       Arabic                vtt, srt, ttml, srv3, srv2, srv1, json3
    hy       Armenian              vtt, srt, ttml, srv3, srv2, srv1, json3
    as       Assamese              vtt, srt, ttml, srv3, srv2, srv1, json3
    ay       Aymara                vtt, srt, ttml, srv3, srv2, srv1, json3
    az       Azerbaijani           vtt, srt, ttml, srv3, srv2, srv1, json3
    bn       Bangla                vtt, srt, ttml, srv3, srv2, srv1, json3
    ba       Bashkir               vtt, srt, ttml, srv3, srv2, srv1, json3
    eu       Basque                vtt, srt, ttml, srv3, srv2, srv1, json3
    be       Belarusian            vtt, srt, ttml, srv3, srv2, srv1, json3
    bho      Bhojpuri              vtt, srt, ttml, srv3, srv2, srv1, json3
    bs       Bosnian               vtt, srt, ttml, srv3, srv2, srv1, json3
    br       Breton                vtt, srt, ttml, srv3, srv2, srv1, json3
    bg       Bulgarian             vtt, srt, ttml, srv3, srv2, srv1, json3
    my       Burmese               vtt, srt, ttml, srv3, srv2, srv1, json3
    ca       Catalan               vtt, srt, ttml, srv3, srv2, srv1, json3
    ceb      Cebuano               vtt, srt, ttml, srv3, srv2, srv1, json3
    zh-Hans  Chinese (Simplified)  vtt, srt, ttml, srv3, srv2, srv1, json3
    zh-Hant  Chinese (Traditional) vtt, srt, ttml, srv3, srv2, srv1, json3
    co       Corsican              vtt, srt, ttml, srv3, srv2, srv1, json3
    hr       Croatian              vtt, srt, ttml, srv3, srv2, srv1, json3
    cs       Czech                 vtt, srt, ttml, srv3, srv2, srv1, json3
    da       Danish                vtt, srt, ttml, srv3, srv2, srv1, json3
    dv       Divehi                vtt, srt, ttml, srv3, srv2, srv1, json3
    nl       Dutch                 vtt, srt, ttml, srv3, srv2, srv1, json3
    dz       Dzongkha              vtt, srt, ttml, srv3, srv2, srv1, json3
    en-orig  English (Original)    vtt, srt, ttml, srv3, srv2, srv1, json3
    en       English               vtt, srt, ttml, srv3, srv2, srv1, json3
    eo       Esperanto             vtt, srt, ttml, srv3, srv2, srv1, json3
    et       Estonian              vtt, srt, ttml, srv3, srv2, srv1, json3
    … (123 lines truncated)
    
    Exit code: 0
    
    `| head -50` was parsed out (50 of 173 total lines shown).
    <truncation_notice>
    Full output written to: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/4d8c0dc0/content.txt
    </truncation_notice>
  4. Devin

    English captions are available. Let me download them now.

    exec(command: cd /tmp && yt-dlp --skip-download --writ…)
    {
      "command": "cd /tmp && yt-dlp --skip-download --write-auto-sub --sub-lang en --sub-format srt -o \"yt_caption\" \"https://www.youtube.com/watch?v=ovrPPSZagPk\" 2>&1"
    }
    In 1Out 128Cache 17,962TTFT 2,973mstool_calls
  5. OutputOutput from command in shell 6071e8:
    Output from command in shell 6071e8:
    WARNING: Your yt-dlp version (2025.12.08) is older than 90 days!
             It is strongly recommended to always use the latest version.
             You installed yt-dlp with pip or using the wheel from PyPi; Use that to update.
             To suppress this warning, add --no-update to your command/config.
    [youtube] Extracting URL: https://www.youtube.com/watch?v=ovrPPSZagPk
    [youtube] ovrPPSZagPk: Downloading webpage
    [youtube] ovrPPSZagPk: Downloading tv client config
    [youtube] ovrPPSZagPk: Downloading player 4918c89a-main
    [youtube] ovrPPSZagPk: Downloading tv player API JSON
    [youtube] ovrPPSZagPk: Downloading android sdkless player API JSON
    [youtube] [jsc:deno] Solving JS challenges using deno
    WARNING: [youtube] [jsc] Remote components challenge solver script (deno) and NPM package (deno) were skipped. These may be required to solve JS challenges. You can enable these downloads with  --remote-components ejs:github  (recommended) or  --remote-components ejs:npm , respectively. For more information and alternatives, refer to  https://github.com/yt-dlp/yt-dlp/wiki/EJS
    WARNING: [youtube] ovrPPSZagPk: n challenge solving failed: Some formats may be missing. Ensure you have a supported JavaScript runtime and challenge solver script distribution installed. Review any warnings presented before this message. For more details, refer to  https://github.com/yt-dlp/yt-dlp/wiki/EJS
    [info] ovrPPSZagPk: Downloading subtitles: en
    [info] ovrPPSZagPk: Downloading 1 format(s): 139-19
    [info] Writing video subtitles to: yt_caption.en.srt
    [download] Destination: yt_caption.en.srt
    
    [download]    1.00KiB at  Unknown B/s (00:00:00)
    [download]    3.00KiB at  Unknown B/s (00:00:00)
    [download]    7.00KiB at    4.92MiB/s (00:00:00)
    [download]   13.73KiB at    3.20MiB/s (00:00:00)
    [download] 100% of   13.73KiB in 00:00:00 at 136.61KiB/s
    
    
    Exit code: 0
  6. Devin
    exec(command: cat /tmp/yt_caption.en.srt)
    {
      "command": "cat /tmp/yt_caption.en.srt"
    }
    In 1Out 63Cache 19,650tool_calls
  7. OutputOutput from command in shell 686e12:
    Output from command in shell 686e12:
    1
    00:00:01,280 --> 00:00:05,920
    The IM Cologne Major is over and instead
    
    2
    00:00:04,000 --> 00:00:07,520
    of watching the games, I spent the whole
    
    3
    00:00:05,920 --> 00:00:09,280
    time looking at what mice the pro
    
    4
    00:00:07,520 --> 00:00:11,759
    players were using. With the release of
    
    5
    00:00:09,280 --> 00:00:14,480
    the Logitech Gro X2 Super Strike and the
    
    6
    00:00:11,759 --> 00:00:16,480
    Razer Viper V4 Pro, we are potentially
    
    7
    00:00:14,480 --> 00:00:19,039
    looking at a massive shift in the Pro
    
    8
    00:00:16,480 --> 00:00:21,199
    Scenes go-to mouse. Today, we're finding
    
    9
    00:00:19,039 --> 00:00:24,000
    out which mouse is the most popular
    
    10
    00:00:21,199 --> 00:00:25,920
    among CS2 pros, what mouse is
    
    11
    00:00:24,000 --> 00:00:27,760
    statistically more likely to win you a
    
    12
    00:00:25,920 --> 00:00:29,920
    major, whether sponsors are forcing
    
    13
    00:00:27,760 --> 00:00:31,920
    players to use garbage, and other
    
    14
    00:00:29,920 --> 00:00:34,399
    delightful fun facts you can bore people
    
    15
    00:00:31,920 --> 00:00:36,960
    with at parties if you get invited to
    
    16
    00:00:34,399 --> 00:00:39,280
    one, or a Discord group chat. The last
    
    17
    00:00:36,960 --> 00:00:42,320
    event I looked at, the Austin Major, had
    
    18
    00:00:39,280 --> 00:00:44,480
    a total of 10 brands. Two of those 10
    
    19
    00:00:42,320 --> 00:00:47,680
    didn't make it this time around as ASUS
    
    20
    00:00:44,480 --> 00:00:50,160
    ROG and Hitcan no longer feature. This
    
    21
    00:00:47,680 --> 00:00:52,559
    time at the Cologne Major, we have 11
    
    22
    00:00:50,160 --> 00:00:54,960
    brands in total with two new brands
    
    23
    00:00:52,559 --> 00:00:57,280
    having their debut in my CS2 analysis
    
    24
    00:00:54,960 --> 00:00:59,680
    videos and one returning brand as
    
    25
    00:00:57,280 --> 00:01:01,120
    Endgame gear has made a comeback. The
    
    26
    00:00:59,680 --> 00:01:03,359
    last time they were featured in my
    
    27
    00:01:01,120 --> 00:01:06,000
    videos was during the very first CS2
    
    28
    00:01:03,359 --> 00:01:08,400
    major in Copenhagen. This time there was
    
    29
    00:01:06,000 --> 00:01:10,640
    only one player, Magix, representing the
    
    30
    00:01:08,400 --> 00:01:12,640
    brand with the OP18K.
    
    31
    00:01:10,640 --> 00:01:14,400
    We also see the inclusion of everyone's
    
    32
    00:01:12,640 --> 00:01:17,439
    favorite budget mouse brand and its
    
    33
    00:01:14,400 --> 00:01:20,640
    first appearance in my CS2 videos, ADK,
    
    34
    00:01:17,439 --> 00:01:22,799
    with Zontics using the A9 Ultimate. The
    
    35
    00:01:20,640 --> 00:01:25,200
    final new brand is one that you would
    
    36
    00:01:22,799 --> 00:01:27,680
    not guess in a million years, unless
    
    37
    00:01:25,200 --> 00:01:29,520
    you're Brazilian. Fallen is using a
    
    38
    00:01:27,680 --> 00:01:31,840
    mouse from his own brand. It's
    
    39
    00:01:29,520 --> 00:01:33,920
    potentially a Fallen Lobo wireless,
    
    40
    00:01:31,840 --> 00:01:36,320
    which comes with a screen on the side.
    
    41
    00:01:33,920 --> 00:01:38,720
    The Steel Series Rival 700's Legacy
    
    42
    00:01:36,320 --> 00:01:41,520
    continues.
    
    43
    00:01:38,720 --> 00:01:44,720
    This weighs around 60 g apparently. It
    
    44
    00:01:41,520 --> 00:01:46,720
    has a 3395 sensor with 1,000 Hz polling.
    
    45
    00:01:44,720 --> 00:01:49,439
    Looks like it has awful coating and
    
    46
    00:01:46,720 --> 00:01:51,840
    costs around $88. You can also buy a
    
    47
    00:01:49,439 --> 00:01:54,240
    Lamzu Maya X for almost $300 from his
    
    48
    00:01:51,840 --> 00:01:56,560
    website if you want. There were two
    
    49
    00:01:54,240 --> 00:01:59,200
    other brands that had just one user and
    
    50
    00:01:56,560 --> 00:02:01,119
    appeared at the Austin Major. WL Mouse
    
    51
    00:01:59,200 --> 00:02:03,680
    featured last time, but Slax has moved
    
    52
    00:02:01,119 --> 00:02:05,600
    away from the Beast X and Sonic from NRG
    
    53
    00:02:03,680 --> 00:02:07,439
    is using one instead. This is literally
    
    54
    00:02:05,600 --> 00:02:09,280
    all I have to work with sometimes.
    
    55
    00:02:07,439 --> 00:02:11,920
    Lambzu has dropped from having three
    
    56
    00:02:09,280 --> 00:02:15,040
    users last year to just one at Cologne
    
    57
    00:02:11,920 --> 00:02:18,480
    with Beast Stick using a Maya X. So,
    
    58
    00:02:15,040 --> 00:02:20,959
    Endgame Gear, ATK, Fallen, Lambzu, and
    
    59
    00:02:18,480 --> 00:02:23,200
    WL mouse all shared the eighth place
    
    60
    00:02:20,959 --> 00:02:25,200
    spot. Final Mouse has gained two
    
    61
    00:02:23,200 --> 00:02:27,440
    additional users from last year to be
    
    62
    00:02:25,200 --> 00:02:30,879
    the sixth most popular mouse brand at
    
    63
    00:02:27,440 --> 00:02:33,280
    the event. The WL mouse betrayer Slax is
    
    64
    00:02:30,879 --> 00:02:36,080
    using the Ultralite X and is joined by
    
    65
    00:02:33,280 --> 00:02:38,480
    major debutants, Symmetry, and Demon of
    
    66
    00:02:36,080 --> 00:02:40,080
    Foot. The next three brands have dropped
    
    67
    00:02:38,480 --> 00:02:42,080
    quite a few users from the previous
    
    68
    00:02:40,080 --> 00:02:44,160
    event. The spreadsheet for this will be
    
    69
    00:02:42,080 --> 00:02:46,480
    available for Patreon supporters on pay
    
    70
    00:02:44,160 --> 00:02:48,319
    tiers, so please consider joining to
    
    71
    00:02:46,480 --> 00:02:50,080
    support the channel. It includes some
    
    72
    00:02:48,319 --> 00:02:52,000
    keyboards and mouse pads and a
    
    73
    00:02:50,080 --> 00:02:54,480
    comparison of mice used by players at
    
    74
    00:02:52,000 --> 00:02:56,400
    both the Austin and Cologne events if
    
    75
    00:02:54,480 --> 00:02:58,720
    you want to see who swapped their mice.
    
    76
    00:02:56,400 --> 00:03:00,959
    We also do giveaways for mice as well.
    
    77
    00:02:58,720 --> 00:03:03,360
    Pulsar ranks as the fifth most popular
    
    78
    00:03:00,959 --> 00:03:05,599
    brand, though their decline in usage is
    
    79
    00:03:03,360 --> 00:03:08,080
    a bit disappointing. Last year, they had
    
    80
    00:03:05,599 --> 00:03:10,239
    a really good uptake in users with 15
    
    81
    00:03:08,080 --> 00:03:13,200
    players using their mice. The most
    
    82
    00:03:10,239 --> 00:03:15,360
    popular being the XES. This year, they
    
    83
    00:03:13,200 --> 00:03:18,159
    have dropped down to just six.
    
    84
    00:03:15,360 --> 00:03:20,720
    Incredibly, there is just one XLite user
    
    85
    00:03:18,159 --> 00:03:24,239
    this time around along with one X2 and
    
    86
    00:03:20,720 --> 00:03:27,360
    one X2H. The remaining three pulsar mice
    
    87
    00:03:24,239 --> 00:03:31,599
    are unbelievably Zywoo's the chosen
    
    88
    00:03:27,360 --> 00:03:34,239
    mouse. Joining Zyu are OC and Bro. The
    
    89
    00:03:31,599 --> 00:03:36,640
    fourth most popular brand is Vaxi, who
    
    90
    00:03:34,239 --> 00:03:39,360
    also dropped users at this event from 14
    
    91
    00:03:36,640 --> 00:03:41,840
    at the Austin Major to seven. Five
    
    92
    00:03:39,360 --> 00:03:44,159
    players were using the Vaxi XE and one
    
    93
    00:03:41,840 --> 00:03:46,400
    was using the MP01SV3
    
    94
    00:03:44,159 --> 00:03:48,000
    and another was using an E1. There is
    
    95
    00:03:46,400 --> 00:03:50,080
    likely a reason for this drop which
    
    96
    00:03:48,000 --> 00:03:52,080
    we'll explore in a moment. The biggest
    
    97
    00:03:50,080 --> 00:03:54,560
    surprise is that Razer has finished
    
    98
    00:03:52,080 --> 00:03:58,080
    third with an 11.3%
    
    99
    00:03:54,560 --> 00:04:00,560
    share, a decline from the 16.9% share
    
    100
    00:03:58,080 --> 00:04:02,959
    they held during the Austin Major.
    
    101
    00:04:00,560 --> 00:04:05,040
    Despite the release of the Viper V4 Pro,
    
    102
    00:04:02,959 --> 00:04:06,959
    they still dropped users. When you
    
    103
    00:04:05,040 --> 00:04:09,439
    consider the Valerant Pro scene adopted
    
    104
    00:04:06,959 --> 00:04:13,439
    it rather quickly, helping Razer to a
    
    105
    00:04:09,439 --> 00:04:16,400
    38.3% share at VCT Santiago, tying with
    
    106
    00:04:13,439 --> 00:04:18,880
    Logitech, this was a surprising outcome.
    
    107
    00:04:16,400 --> 00:04:21,519
    In Cologne, there were just four Viper
    
    108
    00:04:18,880 --> 00:04:24,560
    V4 Pro users. There were three players
    
    109
    00:04:21,519 --> 00:04:27,840
    still using the Viper V3 Pro. The Death
    
    110
    00:04:24,560 --> 00:04:30,320
    V4 Pro had five users, leaving the most
    
    111
    00:04:27,840 --> 00:04:33,600
    popular Razer mouse used at the Cologne
    
    112
    00:04:30,320 --> 00:04:35,919
    Major being the Death Adder V3 Pro. This
    
    113
    00:04:33,600 --> 00:04:38,320
    includes the Hypers Speed. A rather
    
    114
    00:04:35,919 --> 00:04:40,720
    disappointing turnout by Razer standards
    
    115
    00:04:38,320 --> 00:04:43,120
    this time around. The second most
    
    116
    00:04:40,720 --> 00:04:47,759
    popular brand is Zawi, who went from
    
    117
    00:04:43,120 --> 00:04:50,639
    18.1% last year to 24.4 4%. Their most
    
    118
    00:04:47,759 --> 00:04:54,479
    popular mouse by a massive margin is the
    
    119
    00:04:50,639 --> 00:04:57,199
    EC in any size with a 63.4%
    
    120
    00:04:54,479 --> 00:05:00,880
    share, followed by the FK with six,
    
    121
    00:04:57,199 --> 00:05:03,440
    three S2s, two U2s, two ZAS, an
    
    122
    00:05:00,880 --> 00:05:07,199
    unreleased Donk mouse, and an unreleased
    
    123
    00:05:03,440 --> 00:05:09,280
    Erggo mouse used by Blame F. Tabson was
    
    124
    00:05:07,199 --> 00:05:11,360
    also possibly using this as well at some
    
    125
    00:05:09,280 --> 00:05:14,320
    point, but I saw him using a Super
    
    126
    00:05:11,360 --> 00:05:16,240
    Strike first. The model split might be a
    
    127
    00:05:14,320 --> 00:05:18,720
    bit off, but I did notice something
    
    128
    00:05:16,240 --> 00:05:20,880
    else. Previously, there's often been all
    
    129
    00:05:18,720 --> 00:05:22,400
    Logitech or Razer teams. There's an all
    
    130
    00:05:20,880 --> 00:05:24,880
    Logitech team, which we'll take a look
    
    131
    00:05:22,400 --> 00:05:27,520
    at in a moment. This year, there was an
    
    132
    00:05:24,880 --> 00:05:30,479
    all Zawi team. Gaming Gladiators might
    
    133
    00:05:27,520 --> 00:05:32,160
    have all been using a Zawi EC. It's
    
    134
    00:05:30,479 --> 00:05:33,919
    rather hard to confirm this because they
    
    135
    00:05:32,160 --> 00:05:36,000
    got shot on, so there isn't much footage
    
    136
    00:05:33,919 --> 00:05:38,560
    or photos of them, but they are all
    
    137
    00:05:36,000 --> 00:05:41,360
    using a Zoey mouse of some sort. That
    
    138
    00:05:38,560 --> 00:05:44,960
    leaves, unsurprisingly, Logitech as the
    
    139
    00:05:41,360 --> 00:05:49,280
    most popular brand with… (8 chars truncated)
    … (229 lines truncated)
    
    Exit code: 0
    <truncation_notice>
    Full output written to: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/e12846e4/content.txt
    </truncation_notice>
  8. Devin
    read(file_path: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_30…)
    {
      "file_path": "/var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/e12846e4/content.txt"
    }
    In 1Out 101Cache 20,436tool_calls
  9. Output<file-view path="/var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/e12846e4/conte
    <file-view path="/var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/e12846e4/content.txt" start_line="1" end_line="788" total_lines="788">
      1|Output from command in shell 686e12:
      2|1
      3|00:00:01,280 --> 00:00:05,920
      4|The IM Cologne Major is over and instead
      5|
      6|2
      7|00:00:04,000 --> 00:00:07,520
      8|of watching the games, I spent the whole
      9|
     10|3
     11|00:00:05,920 --> 00:00:09,280
     12|time looking at what mice the pro
     13|
     14|4
     15|00:00:07,520 --> 00:00:11,759
     16|players were using. With the release of
     17|
     18|5
     19|00:00:09,280 --> 00:00:14,480
     20|the Logitech Gro X2 Super Strike and the
     21|
     22|6
     23|00:00:11,759 --> 00:00:16,480
     24|Razer Viper V4 Pro, we are potentially
     25|
     26|7
     27|00:00:14,480 --> 00:00:19,039
     28|looking at a massive shift in the Pro
     29|
     30|8
     31|00:00:16,480 --> 00:00:21,199
     32|Scenes go-to mouse. Today, we're finding
     33|
     34|9
     35|00:00:19,039 --> 00:00:24,000
     36|out which mouse is the most popular
     37|
     38|10
     39|00:00:21,199 --> 00:00:25,920
     40|among CS2 pros, what mouse is
     41|
     42|11
     43|00:00:24,000 --> 00:00:27,760
     44|statistically more likely to win you a
     45|
     46|12
     47|00:00:25,920 --> 00:00:29,920
     48|major, whether sponsors are forcing
     49|
     50|13
     51|00:00:27,760 --> 00:00:31,920
     52|players to use garbage, and other
     53|
     54|14
     55|00:00:29,920 --> 00:00:34,399
     56|delightful fun facts you can bore people
     57|
     58|15
     59|00:00:31,920 --> 00:00:36,960
     60|with at parties if you get invited to
     61|
     62|16
     63|00:00:34,399 --> 00:00:39,280
     64|one, or a Discord group chat. The last
     65|
     66|17
     67|00:00:36,960 --> 00:00:42,320
     68|event I looked at, the Austin Major, had
     69|
     70|18
     71|00:00:39,280 --> 00:00:44,480
     72|a total of 10 brands. Two of those 10
     73|
     74|19
     75|00:00:42,320 --> 00:00:47,680
     76|didn't make it this time around as ASUS
     77|
     78|20
     79|00:00:44,480 --> 00:00:50,160
     80|ROG and Hitcan no longer feature. This
     81|
     82|21
     83|00:00:47,680 --> 00:00:52,559
     84|time at the Cologne Major, we have 11
     85|
     86|22
     87|00:00:50,160 --> 00:00:54,960
     88|brands in total with two new brands
     89|
     90|23
     91|00:00:52,559 --> 00:00:57,280
     92|having their debut in my CS2 analysis
     93|
     94|24
     95|00:00:54,960 --> 00:00:59,680
     96|videos and one returning brand as
     97|
     98|25
     99|00:00:57,280 --> 00:01:01,120
    100|Endgame gear has made a comeback. The
    101|
    102|26
    103|00:00:59,680 --> 00:01:03,359
    104|last time they were featured in my
    105|
    106|27
    107|00:01:01,120 --> 00:01:06,000
    108|videos was during the very first CS2
    109|
    110|28
    111|00:01:03,359 --> 00:01:08,400
    112|major in Copenhagen. This time there was
    113|
    114|29
    115|00:01:06,000 --> 00:01:10,640
    116|only one player, Magix, representing the
    117|
    118|30
    119|00:01:08,400 --> 00:01:12,640
    120|brand with the OP18K.
    121|
    122|31
    123|00:01:10,640 --> 00:01:14,400
    124|We also see the inclusion of everyone's
    125|
    126|32
    127|00:01:12,640 --> 00:01:17,439
    128|favorite budget mouse brand and its
    129|
    130|33
    131|00:01:14,400 --> 00:01:20,640
    132|first appearance in my CS2 videos, ADK,
    133|
    134|34
    135|00:01:17,439 --> 00:01:22,799
    136|with Zontics using the A9 Ultimate. The
    137|
    138|35
    139|00:01:20,640 --> 00:01:25,200
    140|final new brand is one that you would
    141|
    142|36
    143|00:01:22,799 --> 00:01:27,680
    144|not guess in a million years, unless
    145|
    146|37
    147|00:01:25,200 --> 00:01:29,520
    148|you're Brazilian. Fallen is using a
    149|
    150|38
    151|00:01:27,680 --> 00:01:31,840
    152|mouse from his own brand. It's
    153|
    154|39
    155|00:01:29,520 --> 00:01:33,920
    156|potentially a Fallen Lobo wireless,
    157|
    158|40
    159|00:01:31,840 --> 00:01:36,320
    160|which comes with a screen on the side.
    161|
    162|41
    163|00:01:33,920 --> 00:01:38,720
    164|The Steel Series Rival 700's Legacy
    165|
    166|42
    167|00:01:36,320 --> 00:01:41,520
    168|continues.
    169|
    170|43
    171|00:01:38,720 --> 00:01:44,720
    172|This weighs around 60 g apparently. It
    173|
    174|44
    175|00:01:41,520 --> 00:01:46,720
    176|has a 3395 sensor with 1,000 Hz polling.
    177|
    178|45
    179|00:01:44,720 --> 00:01:49,439
    180|Looks like it has awful coating and
    181|
    182|46
    183|00:01:46,720 --> 00:01:51,840
    184|costs around $88. You can also buy a
    185|
    186|47
    187|00:01:49,439 --> 00:01:54,240
    188|Lamzu Maya X for almost $300 from his
    189|
    190|48
    191|00:01:51,840 --> 00:01:56,560
    192|website if you want. There were two
    193|
    194|49
    195|00:01:54,240 --> 00:01:59,200
    196|other brands that had just one user and
    197|
    198|50
    199|00:01:56,560 --> 00:02:01,119
    200|appeared at the Austin Major. WL Mouse
    201|
    202|51
    203|00:01:59,200 --> 00:02:03,680
    204|featured last time, but Slax has moved
    205|
    206|52
    207|00:02:01,119 --> 00:02:05,600
    208|away from the Beast X and Sonic from NRG
    209|
    210|53
    211|00:02:03,680 --> 00:02:07,439
    212|is using one instead. This is literally
    213|
    214|54
    215|00:02:05,600 --> 00:02:09,280
    216|all I have to work with sometimes.
    217|
    218|55
    219|00:02:07,439 --> 00:02:11,920
    220|Lambzu has dropped from having three
    221|
    222|56
    223|00:02:09,280 --> 00:02:15,040
    224|users last year to just one at Cologne
    225|
    226|57
    227|00:02:11,920 --> 00:02:18,480
    228|with Beast Stick using a Maya X. So,
    229|
    230|58
    231|00:02:15,040 --> 00:02:20,959
    232|Endgame Gear, ATK, Fallen, Lambzu, and
    233|
    234|59
    235|00:02:18,480 --> 00:02:23,200
    236|WL mouse all shared the eighth place
    237|
    238|60
    239|00:02:20,959 --> 00:02:25,200
    240|spot. Final Mouse has gained two
    241|
    242|61
    243|00:02:23,200 --> 00:02:27,440
    244|additional users from last year to be
    245|
    246|62
    247|00:02:25,200 --> 00:02:30,879
    248|the sixth most popular mouse brand at
    249|
    250|63
    251|00:02:27,440 --> 00:02:33,280
    252|the event. The WL mouse betrayer Slax is
    253|
    254|64
    255|00:02:30,879 --> 00:02:36,080
    256|using the Ultralite X and is joined by
    257|
    258|65
    259|00:02:33,280 --> 00:02:38,480
    260|major debutants, Symmetry, and Demon of
    261|
    262|66
    263|00:02:36,080 --> 00:02:40,080
    264|Foot. The next three brands have dropped
    265|
    266|67
    267|00:02:38,480 --> 00:02:42,080
    268|quite a few users from the previous
    269|
    270|68
    271|00:02:40,080 --> 00:02:44,160
    272|event. The spreadsheet for this will be
    273|
    274|69
    275|00:02:42,080 --> 00:02:46,480
    276|available for Patreon supporters on pay
    277|
    278|70
    279|00:02:44,160 --> 00:02:48,319
    280|tiers, so please consider joining to
    281|
    282|71
    283|00:02:46,480 --> 00:02:50,080
    284|support the channel. It includes some
    285|
    286|72
    287|00:02:48,319 --> 00:02:52,000
    288|keyboards and mouse pads and a
    289|
    290|73
    291|00:02:50,080 --> 00:02:54,480
    292|comparison of mice used by players at
    293|
    294|74
    295|00:02:52,000 --> 00:02:56,400
    296|both the Austin and Cologne events if
    297|
    298|75
    299|00:02:54,480 --> 00:02:58,720
    300|you want to see who swapped their mice.
    301|
    302|76
    303|00:02:56,400 --> 00:03:00,959
    304|We also do giveaways for mice as well.
    305|
    306|77
    307|00:02:58,720 --> 00:03:03,360
    308|Pulsar ranks as the fifth most popular
    309|
    310|78
    311|00:03:00,959 --> 00:03:05,599
    312|brand, though their decline in usage is
    313|
    314|79
    315|00:03:03,360 --> 00:03:08,080
    316|a bit disappointing. Last year, they had
    317|
    318|80
    319|00:03:05,599 --> 00:03:10,239
    320|a really good uptake in users with 15
    321|
    322|81
    323|00:03:08,080 --> 00:03:13,200
    324|players using their mice. The most
    325|
    326|82
    327|00:03:10,239 --> 00:03:15,360
    328|popular being the XES. This year, they
    329|
    330|83
    331|00:03:13,200 --> 00:03:18,159
    332|have dropped down to just six.
    333|
    334|84
    335|00:03:15,360 --> 00:03:20,720
    336|Incredibly, there is just one XLite user
    337|
    338|85
    339|00:03:18,159 --> 00:03:24,239
    340|this time around along with one X2 and
    341|
    342|86
    343|00:03:20,720 --> 00:03:27,360
    344|one X2H. The remaining three pulsar mice
    345|
    346|87
    347|00:03:24,239 --> 00:03:31,599
    348|are unbelievably Zywoo's the chosen
    349|
    350|88
    351|00:03:27,360 --> 00:03:34,239
    352|mouse. Joining Zyu are OC and Bro. The
    353|
    354|89
    355|00:03:31,599 --> 00:03:36,640
    356|fourth most popular brand is Vaxi, who
    357|
    358|90
    359|00:03:34,239 --> 00:03:39,360
    360|also dropped users at this event from 14
    361|
    362|91
    363|00:03:36,640 --> 00:03:41,840
    364|at the Austin Major to seven. Five
    365|
    366|92
    367|00:03:39,360 --> 00:03:44,159
    368|players were using the Vaxi XE and one
    369|
    370|93
    371|00:03:41,840 --> 00:03:46,400
    372|was using the MP01SV3
    373|
    374|94
    375|00:03:44,159 --> 00:03:48,000
    376|and another was using an E1. There is
    377|
    378|95
    379|00:03:46,400 --> 00:03:50,080
    380|likely a reason for this drop which
    381|
    382|96
    383|00:03:48,000 --> 00:03:52,080
    384|we'll explore in a moment. The biggest
    385|
    386|97
    387|00:03:50,080 --> 00:03:54,560
    388|surprise is that Razer has finished
    389|
    390|98
    391|00:03:52,080 --> 00:03:58,080
    392|third with an 11.3%
    393|
    394|99
    395|00:03:54,560 --> 00:04:00,560
    396|share, a decline from the 16.9% share
    397|
    398|100
    399|00:03:58,080 --> 00:04:02,959
    400|they held during the Austin Major.
    401|
    402|101
    403|00:04:00,560 --> 00:04:05,040
    404|Despite the release of the Viper V4 Pro,
    405|
    406|102
    407|00:04:02,959 --> 00:04:06,959
    408|they still dropped users. When you
    409|
    410|103
    411|00:04:05,040 --> 00:04:09,439
    412|consider the Valerant Pro scene adopted
    413|
    414|104
    415|00:04:06,959 --> 00:04:13,439
    416|it rather quickly, helping Razer to a
    417|
    418|105
    419|00:04:09,439 --> 00:04:16,400
    420|38.3% share at VCT Santiago, tying with
    421|
    422|106
    423|00:04:13,439 --> 00:04:18,880
    424|Logitech, this was a surprising outcome.
    425|
    426|107
    427|00:04:16,400 --> 00:04:21,519
    428|In Cologne, there were just four Viper
    429|
    430|108
    431|00:04:18,880 --> 00:04:24,560
    432|V4 Pro users. There were three players
    433|
    434|109
    435|00:04:21,519 --> 00:04:27,840
    436|still using the Viper V3 Pro. The Death
    437|
    438|110
    439|00:04:24,560 --> 00:04:30,320
    440|V4 Pro had five users, leaving the most
    441|
    442|111
    443|00:04:27,840 --> 00:04:33,600
    444|popular Razer mouse used at the Cologne
    445|
    446|112
    447|00:04:30,320 --> 00:04:35,919
    448|Major being the Death Adder V3 Pro. This
    449|
    450|113
    451|00:04:33,600 --> 00:04:38,320
    452|includes the Hypers Speed. A rather
    453|
    454|114
    455|00:04:35,919 --> 00:04:40,720
    456|disappointing turnout by Razer standards
    457|
    458|115
    459|00:04:38,320 --> 00:04:43,120
    460|this time around. The second most
    461|
    462|116
    463|00:04:40,720 --> 00:04:47,759
    464|popular brand is Zawi, who went from
    465|
    466|117
    467|00:04:43,120 --> 00:04:50,639
    468|18.1% last year to 24.4 4%. Their most
    469|
    470|118
    471|00:04:47,759 --> 00:04:54,479
    472|popular mouse by a massive margin is the
    473|
    474|119
    475|00:04:50,639 --> 00:04:57,199
    476|EC in any size with a 63.4%
    477|
    478|120
    479|00:04:54,479 --> 00:05:00,880
    480|share, followed by the FK with six,
    481|
    482|121
    483|00:04:57,199 --> 00:05:03,440
    484|three S2s, two U2s, two ZAS, an
    485|
    486|122
    487|00:05:00,880 --> 00:05:07,199
    488|unreleased Donk mouse, and an unreleased
    489|
    490|123
    491|00:05:03,440 --> 00:05:09,280
    492|Erggo mouse used by Blame F. Tabson was
    493|
    494|124
    495|00:05:07,199 --> 00:05:11,360
    496|also possibly using this as well at some
    497|
    498|125
    499|00:05:09,280 --> 00:05:14,320
    500|point, but I saw him using a Super
    501|
    502|126
    503|00:05:11,360 --> 00:05:16,240
    504|Strike first. The model split might be a
    505|
    506|127
    507|00:05:14,320 --> 00:05:18,720
    508|bit off, but I did notice something
    509|
    510|128
    511|00:05:16,240 --> 00:05:20,880
    512|else. Previously, there's often been all
    513|
    514|129
    515|00:05:18,720 --> 00:05:22,400
    516|Logitech or Razer teams. There's an all
    517|
    518|130
    519|00:05:20,880 --> 00:05:24,880
    520|Logitech team, which we'll take a look
    521|
    522|131
    523|00:05:22,400 --> 00:05:27,520
    524|at in a moment. This year, there was an
    525|
    526|132
    527|00:05:24,880 --> 00:05:30,479
    528|all Zawi team. Gaming Gladiators might
    529|
    530|133
    531|00:05:27,520 --> 00:05:32,160
    532|have all been using a Zawi EC. It's
    533|
    534|134
    535|00:05:30,479 --> 00:05:33,919
    536|rather hard to confirm this because they
    537|
    538|135
    539|00:05:32,160 --> 00:05:36,000
    540|got shot on, so there isn't much footage
    541|
    542|136
    543|00:05:33,919 --> 00:05:38,560
    544|or photos of them, but they are all
    545|
    546|137
    547|00:05:36,000 --> 00:05:41,360
    548|using a Zoey mouse of some sort. That
    549|
    550|138
    551|00:05:38,560 --> 00:05:44,960
    552|leaves, unsurprisingly, Logitech as the
    553|
    554|139
    555|00:05:41,360 --> 00:05:49,280
    556|most popular brand with a 51.3%
    557|
    558|140
    559|00:05:44,960 --> 00:05:52,639
    560|share or 82 users, up from 42.5%
    561|
    562|141
    563|00:05:49,280 --> 00:05:54,560
    564|or 68 users from the Austin Major. After
    565|
    566|142
    567|00:05:52,639 --> 00:05:56,639
    568|what looked to be a downward trend, the
    569|
    570|143
    571|00:05:54,560 --> 00:05:59,360
    572|Super Strike seems to have reinvigorated
    573|
    574|144
    575|00:05:56,639 --> 00:06:02,400
    576|the protein with 31.3%
    577|
    578|145
    579|00:05:59,360 --> 00:06:04,880
    580|or 66 players using a Super Strike.
    581|
    582|146
    583|00:06:02,400 --> 00:06:07,280
    584|There were 30 Superite users.
    585|
    586|147
    587|00:06:04,880 --> 00:06:09,759
    588|Interestingly, despite Monzy having a
    589|
    590|148
    591|00:06:07,280 --> 00:06:11,680
    592|15-second ad for the Super Strike, he
    593|
    594|149
    595|00:06:09,759 --> 00:06:14,240
    596|doesn't actually use it. One team,
    597|
    598|150
    599|00:06:11,680 --> 00:06:16,560
    600|Na'vi, had all their players using a
    601|
    602|151
    603|00:06:14,240 --> 00:06:19,440
    604|Logitech mouse. There were two other
    605|
    606|152
    607|00:06:16,560 --> 00:06:22,880
    608|Logitech mice. Ins of Fly Quest was
    609|
    610|153
    611|00:06:19,440 --> 00:06:26,080
    612|actually using a Gro 2, and I'm around
    613|
    614|154
    615|00:06:22,880 --> 00:06:28,720
    616|60% sure that Biomass from Monte was
    617|
    618|155
    619|00:06:26,080 --> 00:06:30,880
    620|using a Superite 2 Dex. So, it's looking
    621|
    622|156
    623|00:06:28,720 --> 00:06:35,120
    624|like the Superite Dex might be a
    625|
    626|157
    627|00:06:30,880 --> 00:06:37,199
    628|Superite dud for the pro scene.
    629|
    630|158
    631|00:06:35,120 --> 00:06:39,520
    632|What's even more interesting is that in
    633|
    634|159
    635|00:06:37,199 --> 00:06:42,639
    636|the grand finals, there was just one
    637|
    638|160
    639|00:06:39,520 --> 00:06:45,199
    640|player using the Super Strike. In fact,
    641|
    642|161
    643|00:06:42,639 --> 00:06:48,000
    644|Razer was the most popular choice in the
    645|
    646|162
    647|00:06:45,199 --> 00:06:51,120
    648|grand finals, and three out of the five
    649|
    650|163
    651|00:06:48,000 --> 00:06:53,759
    652|players on Falcons were using Razer. So,
    653|
    654|164
    655|00:06:51,120 --> 00:06:55,840
    656|by this infallible logic, you're more
    657|
    658|165
    659|00:06:53,759 --> 00:06:57,759
    660|likely to win a CS2 major with the Razer
    661|
    662|166
    663|00:06:55,840 --> 00:06:59,919
    664|Mouse or if you're backed by a pro
    665|
    666|167
    667|00:06:57,759 --> 00:07:01,680
    668|state. I know some little rap scallion
    669|
    670|168
    671|00:06:59,919 --> 00:07:03,599
    672|is going to be furiously typing about
    673|
    674|169
    675|00:07:01,680 --> 00:07:05,840
    676|how they're sponsored, blah blah blah
    677|
    678|170
    679|00:07:03,599 --> 00:07:08,000
    680|blah. Give your fingers a rest, my
    681|
    682|171
    683|00:07:05,840 --> 00:07:09,759
    684|child. I've checked this as well. I went
    685|
    686|172
    687|00:07:08,000 --> 00:07:11,759
    688|through every team, checked their
    689|
    690|173
    691|00:07:09,759 --> 00:07:15,280
    692|sponsors, and I can confirm that
    693|
    694|174
    695|00:07:11,759 --> 00:07:17,280
    696|approximately 27 out of 160 players
    697|
    698|175
    699|00:07:15,280 --> 00:07:19,599
    700|could have been contractually obligated
    701|
    702|176
    703|00:07:17,280 --> 00:07:22,639
    704|to use a certain mouse. I went one
    705|
    706|177
    707|00:07:19,599 --> 00:07:24,639
    708|further. Nico, Zyu, and Monzy are
    709|
    710|178
    711|00:07:22,639 --> 00:07:26,479
    712|possibly contractually obligated to use
    713|
    714|179
    715|00:07:24,639 --> 00:07:29,120
    716|certain mice because they appear
    717|
    718|180
    719|00:07:26,479 --> 00:07:32,400
    720|directly in advertisements. So, that's
    721|
    722|181
    723|00:07:29,120 --> 00:07:34,080
    724|around 30 out of 160 players. I even
    725|
    726|182
    727|00:07:32,400 --> 00:07:35,840
    728|checked keyboards and that didn't seem
    729|
    730|183
    731|00:07:34,080 --> 00:07:38,240
    732|consistent either. If a team was
    733|
    734|184
    735|00:07:35,840 --> 00:07:40,160
    736|sponsored by Logitech or Razer, the
    737|
    738|185
    739|00:07:38,240 --> 00:07:42,880
    740|players would likely be using one of
    741|
    742|186
    743|00:07:40,160 --> 00:07:44,960
    744|their keyboards. Same with Asus ROG.
    745|
    746|187
    747|00:07:42,880 --> 00:07:46,960
    748|Mouse pads seem to be the same as mice,
    749|
    750|188
    751|00:07:44,960 --> 00:07:49,199
    752|but some players had their logos covered
    753|
    754|189
    755|00:07:46,960 --> 00:07:51,280
    756|up and others on the same team didn't.
    757|
    758|190
    759|00:07:49,199 --> 00:07:54,240
    760|Even then, across the 32 competing
    761|
    762|191
    763|00:07:51,280 --> 00:07:56,400
    764|teams, only 18 had partnerships with
    765|
    766|192
    767|00:07:54,240 --> 00:07:58,240
    768|companies that make peripherals. So,
    769|
    770|193
    771|00:07:56,400 --> 00:08:00,000
    772|pros are pros because they're very good
    773|
    774|194
    775|00:07:58,240 --> 00:08:01,599
    776|at the game. They don't need excuses
    777|
    778|195
    779|00:08:00,000 --> 00:08:04,840
    780|like it's the mouse's fault why they
    781|
    782|196
    783|00:08:01,599 --> 00:08:04,840
    784|didn't win.
    785|
    786|
    787|
    788|Exit code: 0
    </file-view>
  10. Devin

    Here's a summary of the video:


    CS2 Pro Mouse Usage at the IEM Cologne Major — Summary

    The video is a data-driven breakdown of which gaming mice CS2 pro players used at the IEM Cologne Major, compared to the previous Austin Major.

    Brand Rankings (Cologne Major)

    RankBrandShare / Notes
    1stLogitech51.3% (82 players) — up from 42.5% at Austin. The new G Pro X2 Super Strike drove adoption, with 66 players on it.
    2ndZowie24.4% — up from 18.1%. The EC series dominated with 63.4% share within the brand. Zowie even had one all-Zowie team (Gaming Gladiators). An unreleased "Donk mouse" and an unreleased ergo model were spotted.
    3rdRazer11.3% — down from 16.9%, a surprise given the new Viper V4 Pro launch. The DeathAdder V3 Pro was their most-used mouse. Notably, Razer was the top brand in the grand finals (Falcons had 3/5 players on Razer).
    4thVaxeeDropped from 14 to 7 users.
    5thPulsarDropped from 15 to 6 users. Notably, ZywOo uses their mouse.
    6thFinalmouseGained 2 users vs. last year (Slax, Symmetry, Demon on the Ultralite X).
    7th–8thEndgame Gear, ATK, Fallen (brand), Lambzu, WL Mouse1 user each

    Notable Highlights

    • Logitech Super Strike surge: 66 of 160 players used it. Ironically, Monzy, who appeared in a 15-second Super Strike ad, doesn't actually use it.
    • Fallen's own brand mouse: The Brazilian legend used a mouse from his own brand ("Fallen Lobo Wireless"), featuring a screen on the side — drawing a joking comparison to the SteelSeries Rival 700.
    • Grand Finals stat: The Super Strike had just one user in the grand finals. Razer was statistically the most common mouse among finalists.
    • Sponsorship check: ~27–30 out of 160 players could be contractually obligated to use a specific mouse. Only 18 of 32 teams had peripheral partnerships. The conclusion: sponsorships have relatively minor influence on mouse choice overall.
    • Logitech Super Lite Dex: Only ~1 confirmed user (Biomass from Monte), suggesting the "Superite Dex" may be a flop in the pro scene.

    Takeaway

    Logitech has a dominant and growing grip on the CS2 pro scene, with the G Pro X2 Super Strike being the new go-to. Zowie is a strong #2. The Razer Viper V4 Pro underperformed expectations at this event despite doing well in Valorant pro play. Sponsor pressure is real but not the dominant factor in mouse choice.

    In 1Out 812Cache 24,872TTFT 1,520ms