Models keep dumping base knowledge into prompts they'll have tomorrow anyway
teropa · x · 2026-10-30
teropa quotes an episode of "AI that works" by dexhorthy and aaronvi, praised as a good example of building an AI pipeline by starting with the simplest thing that works and iterating over time, with real-world use-cases. His quip: models constantly bake base knowledge into prompts and skills as if that knowledge wouldn't still be there tomorrow — needless redundancy.
More from coding & agent
- Anthropic launches Claude Duet, a proactive agent powered by Opus 5.5 — joellewenstein · 2026-10-30
- The Future of MCP: 6 Shifts That Will Shape Production AI Agents — MaryamMiradi · 2026-10-30
- Spring AI 2.1 adds VectorStore.upsert for apps that bring their own embeddings — therealdanvega · 2026-10-30
- Auditing an LLM-built knowledge graph: 0 of 186 facts matched verbatim, 1/3 of edges hit wrong entities — JeremyCMorgan · 2026-10-30
- Same agent harness, opposite rankings: TB4 benchmark drama exposes eval chaos — lunwang1996 · 2026-10-30
- The eternal eval debugging meme: ask the vendor if it's data or harness, it's data — dejavucoder · 2026-10-30