AI Models 323 posts

Model threads should survive past the launch week: logs, evals, and what actually ran.

Sort:

AI Models — All Posts

A 7-million-parameter model outclasses GPT-4 on ARC’s abstract reasoning tests
Sentiment models ignore context by reducing reviews to one-size-fits-all labels
Use Placebo Proofs to Stop AI Agents from Shipping Broken Code
Stop LLM planning from becoming a chaotic mess of technical jargon
OpenAI is transforming ChatGPT into a digital shopping mall for its users.
OneRep Shows Why Local AI Fitness Apps Are Harder Than They Look
Live API challenges with Gemini 1.5 Flash vs. Pro require careful model selection.