AIModels.fyi
  • Home
  • Creators
  • Models
  • Notes
  • Advertise
  • 🎉 Support my work
Sign in Subscribe

Latest

Hallucination reduction strategies.

LLMs will lie forever

Hallucinations are never going away. How can we reduce them?
aimodels-fyi Sep 25, 2024
Creed making an acronym but not about AI

AI can (kinda) generate novel ideas

LLMs have some brainstorming limitations.
aimodels-fyi Sep 13, 2024
AI agents can collude using hidden messages!

AI agents can collude using hidden messages!

LLMs can hide their real messages in unsuspicious chit-chat
aimodels-fyi Sep 4, 2024
🥇Top ML papers of the week

🥇Top ML papers of the week

The top ML papers of the week (Aug 23 — Aug 30)
aimodels-fyi Aug 30, 2024
Training on code improves LLM performance on non-coding tasks

Training on code improves LLM performance on non-coding tasks

Adding code to your training data makes your LLM better at non-coding tasks too
aimodels-fyi Aug 30, 2024
Experiment design

🧠 Training on code improves LLM performance on non-coding tasks

Adding code to your training data makes your LLM better at non-coding tasks too
aimodels-fyi Aug 25, 2024
LLMs can speak in JPEG

LLMs can speak in JPEG

By studying “secret” messages (JPEGs), LLMs can eventually learn to write them.
aimodels-fyi Aug 22, 2024

Subscribe to AIModels.fyi

Don't miss out on the latest news. Sign up now to get access to the library of members-only articles.
  • Sign up
AIModels.fyi © 2025. Powered by Ghost