GPT-5

entities · 7 notes linked

Related: Openai · Gemini · Large Language Models · AI Agents · Claude · Model Evaluation · AI Safety · Claude Opus

Notes

• AI #172: The First Fable — Weekly roundup excluding the Fable model itself
• Agent, Know Thyself! (and bid accordingly) — Markets to route AI agent tasks via self-assessment
• How to Build An AI Agent with Function Calling and GPT-5 | Towards Data Science — Building a web-search AI agent via GPT-5 function calling
• LLM Leaderboard - Comparison of over 100 AI models from OpenAI, Google, DeepSeek & others — Artificial Analysis leaderboard ranking 100+ LLMs
• Learning to Replicate Expert Judgment in Financial Tasks — Fine-tuned LLM beats frontier models at financial info triage
• MathNet — Explore 30,000+ Olympiad Math Problems — Large-scale multilingual Olympiad math benchmark for LLM reasoning and retrieval
• OpenAI is throwing everything into building a fully automated researcher — OpenAI's North Star automated AI researcher agent