anthropics/original_performance_takehome
- Source
- GitHub
- First trending
- Category
- Other
- GitHub stars
- 4,156
- Main language
- Python
This page introduces an external open-source repository. It is not an HDATF product.
What it does
Anthropic's former performance take-home exercise for job applicants, where the goal is to lower a score measured in clock cycles of a simulated machine. The README compares results from Claude models with human performance.
How it helps ATF
Not related to our products. Listed because it appeared in the ranked lists.
License
No license No license file found. Without a license, reuse of the code is not permitted by default.
More in this category
- xai-org/x-algorithm
The core code that decides which posts appear in the For You feed on X. It mixes posts from followed accounts with posts found through ML-based retrieval, filters them and ranks them with a transformer model. - ZhuLinsen/daily_stock_analysis
An LLM-based stock analysis system for markets including A-shares, Hong Kong and US stocks. It gathers quotes and news, builds a daily decision dashboard report, and pushes it to channels such as WeCom, Feishu, Telegram, Slack or email. - ran-j/PS2Recomp
An experimental tool that statically recompiles PlayStation 2 ELF binaries into C++ and provides a runtime to run the generated code, aimed at native PC ports. - Universal-Commerce-Protocol/ucp
UCP is an open specification that lets platforms such as AI agents, businesses, payment service providers and credential providers exchange commerce data. It defines capabilities like Checkout and extensions like Discounts so agents can find products and complete purchases. - asgeirtj/system_prompts_leaks
A collection of system prompts extracted from AI chatbots and coding tools such as ChatGPT, Claude, Claude Code, Codex, Gemini, Grok and Cursor, kept verbatim. It is updated regularly.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.