Cursor 1.0 is out now! Cursor can now review your code, remember its mistakes, and work on dozens of tasks in the background.
We have been experimenting recently with replacing Figma with React and an AI IDE (@cursor_ai) for our UI design team. Instead of static visuals, designers now create functional prototypes directly in React. With some basic alignment with Engineering—covering libraries,…
We shipped several upgrades to our Apply model this month. It can now accurately edit over 5k tokens per second. Try it out in chat, composer, or agent!
Most people don't grasp the complexity of enterprise products. I analyzed 1,000 enterprise repositories in our portfolio to test LLM context limits: Full dataset: 4B tokens needed. Average repository: 4M tokens. Largest repository: 300M+ tokens. 50% of repos fit in 200K…
🧵 We are automating bug fixing at enterprise scale with our custom AI Agents, fixing hundreds of defects regularly. The main challenge is identifying the relevant repository for a bug, especially since some enterprise products have hundreds of repositories. Here's what works:
🌟 Build a Customer Support Bot in LangGraph🤖💬 Learn to build a customer support bot that can research and manage bookings for flights, transportation, hotels, and excursions. Starting with a capable (albeit unpredictable) zero-shot agent, learn to progressively add…
🔨 Standardized tool calling 🔨 **tl;dr;** we've made some big improvements to working with tools across model providers! 🧰 A new `tool_calls` field directly on messages with the same schema for all providers. 🤖 A new `ToolCallingAgent`. Supports any model with tool calling…
🤖Agent Supervisor with Anthropic We've put a lot of work into LangGraph to make it the best run time for agents. Most of the examples are with OpenAI, but @eucheetan just open-sourced an example with @AnthropicAI models github.com/prof-frink-lab…
Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is…
# automating software engineering In my mind, automating software engineering will look similar to automating driving. E.g. in self-driving the progression of increasing autonomy and higher abstraction looks something like: 1. first the human performs all driving actions…
Today we're excited to introduce Devin, the first AI software engineer. Devin is the new state-of-the-art on the SWE-Bench coding benchmark, has successfully passed practical engineering interviews from leading AI companies, and has even completed real jobs on Upwork. Devin is…
⚔️RAG Arena There's so many RAG strategies out there - how do you decide which one is best? Run them in battle mode: the same question with 2 different strategies. Compare and vote for winner Awesome project by @mendableai! Inspired by @lmsysorg RAGArena.com
United States Tren
- 1. Bama 21.9K posts
- 2. Mateer 6,794 posts
- 3. Woodley 10.1K posts
- 4. Anderson Silva 5,908 posts
- 5. #CFBPlayoff 9,739 posts
- 6. Epstein 972K posts
- 7. Ty Simpson 2,395 posts
- 8. #JakeJoshua 22.5K posts
- 9. Bill Clinton 123K posts
- 10. #SmackDown 14K posts
- 11. DeBoer 5,701 posts
- 12. #RollTide 7,186 posts
- 13. Maxey 3,123 posts
- 14. Ryan Williams N/A
- 15. Sixers 4,164 posts
- 16. #BoomerSooner 7,463 posts
- 17. VJ Edgecombe N/A
- 18. Zabien Brown N/A
- 19. Pick 6 5,321 posts
- 20. Andre Drummond N/A
Something went wrong.
Something went wrong.