What to build instead of AI agents(decodingml.substack.com)

192 points by giuliomagnifico 1 year ago | 104 comments

Show HN: Sentinel – open-source QA agent that reads your code before it clicks(blog.simbastack.com)

11 points by asenna 3 months ago | 1 comments

DeepSeek R1's recipe to replicate o1 and the future of reasoning LMs(interconnects.ai)

3 points by Philpax 1 year ago | 0 comments

How Novy Built Zelma for Emily Oster Using OpenAI and Postgres(stepchange.work)

10 points by niallohiggins 2 years ago | 0 comments

Unrolling the Codex agent loop(openai.com)

423 points by tosh 9 months ago | 195 comments

OpenAI engineering blog post by Michael Bolin explaining how the Codex CLI software agent's agent loop works.

GPT-5.2(openai.com)

125 points by meetpateltech 10 months ago | 37 comments

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

LLM-powered tools amplify developer capabilities rather than replacing them(matthewsinclair.com)

323 points by matthewsinclair 1 year ago | 214 comments

Blog post by Matthew Sinclair arguing that LLM-powered programming tools act like a mech suit amplifying developers rather than replacing them.

You should write an agent(fly.io)

944 points by tabletcorry 11 months ago | 375 comments

Fly.io blog post arguing that every developer should build their own LLM agent to understand how agents work.

My finetuned models beat OpenAI's GPT-4(mlops.systems)

376 points by majc2 2 years ago | 86 comments

Blog post evaluating finetuned Mistral, Llama3 and Solar LLMs against OpenAI's GPT-4 on accuracy for structured data extraction from press releases.

LLMs and Programming in the first days of 2024(antirez.com)

355 points by nalgeon 2 years ago | 230 comments

Intended to be antirez's blog post on using LLMs for programming in early 2024, but the capture shows a Redis-branded 404 error page.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 467 comments

Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.