Step-by-step guide to trace LLM behavior origins
gerardsans · x · 2026-08-20
Gerard Sans provided a step-by-step guide to identify where a specific LLM behavior originates, ranked by usual suspects: 1) Training data, 2) Pre-training, 3) Post-training (RLHF/RL), 4) Deployment (system prompt, UX/UI, API), 5) Inference (prompt, context, tools). He also warned against confusing lab narratives for funding with actual science.
Related event: A Five-Step Guide to Tracing LLM Behavior Origins(2 posts)→
More from coding & agent
- Short Film FARÖ Behind the Scenes: Using Invideo Agent for Production — gen_ericai · 2026-08-20
- Developer rebuilds classic iBeer app using React Native and WebGPU physics — JoshuaJBouw · 2026-08-20
- Together AI Releases Hallmark: An Anti-Slop Design Skill for AI Coding Tools — dotey · 2026-08-20
- Google Engineer Breaks Down Agents: LLMs in a Loop and the Reality Gap — bigdata · 2026-08-20
- 12 browser tasks automated with OpenAI: from bookkeeping to form filling — gdb · 2026-08-20
- Deep Dive: Instinct, Grok Bots, and ChatGPT Work Compared — illscience · 2026-08-20