Вам может понравиться
In building AI agents @cline , we've identified three mind viruses Mind Viruses are seductive ideas that sound smart, but don’t work in practice. 1. Multi-Agent Orchestration 2. RAG (Retrieval Augmented Generation) 3. More Instructions = Better Results Let's explore why!
New @MistralAI cookbook: Self-Supervised Prompt Optimization ❌ Prompt engineering... sucks. It's a non-standard process, heavily relying on trial and error and difficult to standardize 🤩 Luckily, we can automate it using ✨prompt optimization✨, investigated in recent works…
AI agent that turns GitHub codebases into step-by-step tutorials with diagrams and code summaries
my secret to writing good docs is "never put two paragraphs in a row"
It took me a little while but I am finally reposting this tutorial on my (new) personal website / blog. It should be easier to share and read then a X article, let me know what you think! maximerivest[.]com
![MaximeRivest's tweet image. It took me a little while but I am finally reposting this tutorial on my (new) personal website / blog.
It should be easier to share and read then a X article, let me know what you think!
maximerivest[.]com](https://pbs.twimg.com/media/GvQVLVUWAAAyalA.jpg)
"Fundamental" truths about software: - Code is liability - The more code you have, the more bugs you tend to have - The more complex a system, the more important architecture becomes - Writing maintainable code is a lot more effort than just getting it to work
Everyone: GitHub Desktop is better! No, VS Code! Me: ...I just use `git add -p`. Walks you through each change, hunk for hunk, and lets you accept with `y`. It’s like a mini code review before you commit. Pair that with dandavison/delta, and you get syntax highlighting too 👀
open-source tool for parsing PDFs, Word, and PowerPoint for LLMs
This makes quick experiments so much easier
This is insane. Google dropped the most powerful UI designer in the world. You just describe the app, and it generates the code. It’s called Stitch. Here’s how it works:
OK, I’ve made up my mind. After testing Qwen3 models in real-world tasks like agentic workflows, parallel function calls, RAG, MCP, QA, long chats, long context… 🔥 Qwen3-4B = reasoning ON 🧠 Qwen3-32B = reasoning OFF Size isn’t everything. Reasoning is.
Let's build a multi-agent book writer, powered Qwen3 (100% local):
Announcing SmartPDFs! Summarize any PDF into beautiful sections. 100% free and open source. smartpdfs.ai
This guy literally saved 100+ dev hours with this one-page guide
United States Тренды
- 1. Expedition 33 22.1K posts
- 2. GOTY 14.5K posts
- 3. Moana 20.4K posts
- 4. Sonic 3 4,628 posts
- 5. #TheGameAwards 25K posts
- 6. Cher 18.2K posts
- 7. Zelda 47.6K posts
- 8. Clair Obscur 14K posts
- 9. #IDontWantToOverreactBUT 1,429 posts
- 10. Comey 20.9K posts
- 11. Hades 2 11.8K posts
- 12. #RestoreTheSnyderVerse 27.6K posts
- 13. #TSCollection 1,530 posts
- 14. Cruz 45.7K posts
- 15. FEMA 4,141 posts
- 16. Split Fiction 4,012 posts
- 17. Silksong 31.7K posts
- 18. Tyrod Taylor 2,275 posts
- 19. #MondayMotivation 43.7K posts
- 20. Donkey Kong 9,613 posts
Вам может понравиться
Something went wrong.
Something went wrong.