Context engineering field notes: poisoning, distraction, confusion and clash
sharpeye_wnl · x · 2026-11-09
The author shares notes from reading up on context engineering, with screenshots covering Anthropic's "Effective context engineering for AI agents". Key taxonomy of context failure modes: context poisoning (hallucinations enter context), context distraction (long context pulls attention from training data, worse for smaller models), context confusion (irrelevant info/excess tools degrade judgment), and context clash (conflicting information). The fix is information management, and RAG is not dead.
More from coding & agent
- dair-ai founder: own your evals — public benchmarks won't tell you what to ship — dair_ai · 2026-11-09
- Open-source video-to-game: agent rebuilds 31 playable games from clips, ~$6 each — songguoxiansen · 2026-11-09
- 'Agent swarms' is funny branding — you wouldn't call coworkers a swarm — round · 2026-11-09
- 179 blocked tool calls were mostly false positives; a re-verification loop is coming — yb2698 · 2026-11-09
- 179 reward-hacking tool calls blocked during agent RL training, just 0.04% of total — yb2698 · 2026-11-09
- Agent RL for three models cost $1,177 total; LFM3 gained 43% tool efficiency — yb2698 · 2026-11-09