ai programming
AI lowers the barrier to getting started on anything, which means people start doing far more. But to do great work still has a long tail of execution, judgment, creativity, and knowledge about the specific domain, which means AI replaces far fewer jobs than we think.
Billions worth of system prompts are exposed in a single repo. The scale of IP leaks is remarkable in the LLM era. https://t.co/903AkTXE1c
GPT-4.1 can now crawl! š„
It finds pages, re-ranks them by relevance, and navigates websites with @OpenAIās new GPT-4.1, delivering exactly what you need, structured and ready to use.
Powered by OpenAIās latest model for fast, intelligent responses and @firecrawl_dev! https://t.co/CR43X6sWdH
It's not enough to build software with AI, you need to be a 10x AI software engineer.
All the best teams are parallelizing their AI software use and churning out 25-50 meaningful commits / engineer / day.
The Claude Code best practices guide is an absolute goldmine of tips https://t.co/z0M1VYmRNL
I think the snappily titled "gemma3:27b-it-qat" may be my new favorite local model - needs 22GB of RAM on my Mac (I'm running it via Ollama, Open WebUI and Tailscale so I can access it from my phone too) and so far it seems extremely capable https://t.co/DnKYL02hRn
Itās definitely worth reading this post for anyone using Claude code. TIL that the word āultrathinkā will result in maximum thinking
Lots of other great tips in here
https://t.co/ETS1eaqh5V... See more
https://t.co/CQinEocACx
OpenAI has published a new prompting guide for GPT-4.1
Agentic prompt that OpenAI used to achieve its highest score on SWE-bench Verified is added here and blog link in 2nd post.
---------------------------------------------------------
You will be tasked to fix an issue from https://t.co/prWJrFZ88m