Anthropic engineer's 4-type ambition framework plus a prompt-rewriting technique
lmoroney · x · 2026-10-16
Felix Rieseberg (Anthropic) sorts AI ambition into four types: Speed (same work faster), Altitude (ask for the outcome you care about, e.g. keep apps crash-free), Depth (work like a field-leading expert with raw data and outside verification), and Range (borrow methods from other fields by describing tasks as verbs). He also shares a prompt that asks the model what a top professional would do that you didn't ask for, then rewrites your prompt accordingly.
More from coding & agent
- OpenAI's Live API adds Decisions API for ~200ms real-time voice app decisions — juberti · 2026-10-16
- Open-source anatomy-reveal skill turns Claude into an exploded-view motion design studio — msharmas · 2026-10-16
- New paper 'Scaling Discovery Requires Forgetting': making AutoResearch agents forget to escape idea basins — rbhar90 · 2026-10-16
- Survey: AI agent evaluation is getting realistic but still fails to measure safety and reliability — burkov · 2026-10-16
- First AA-AgentPerf results: NVIDIA Vera Rubin NVL72 delivers up to 5.7x throughput per MW vs GB300 — ArtificialAnlys · 2026-10-16
- 14 open-source LLM observability tools to know in 2026, from Langfuse to Laminar — TheTuringPost · 2026-10-16