Models got less conversational as they got agentic — here's how to get a thinking partner back
evielync · x · 2026-09-11
The author laments that as models became more agentic, they stopped being good conversation partners — the moment you describe a problem, they rush off to build instead of sparring. Her fixes: use a less agentic model like Sonnet, turn down the effort level, and open with 'Let's spar — help me think this through before we build anything.' A practical prompt-level workaround for those who want AI as a thinking partner, not just an executor.
More from coding & agent
- Lightfield Raises Series A to Rebuild CRM as a 'Business World Model' for Agents — dair_ai · 2026-09-11
- 95% local AI + 5% GPT-6: a full basketball tracking pipeline breakdown — TheMoonMidas · 2026-09-11
- NutPrint turns your Claude Code water footprint into almonds, right in the status bar — james_mtc · 2026-09-11
- Sentry CEO: Building a game bot starts with a mini engine of the game itself — zeeg · 2026-09-11
- Astral's goal: installing CPython via uv should get you the fastest build — charliermarsh · 2026-09-11
- python-build-standalone measured fastest CPython: 10% faster than Homebrew, 18% than official Docker — charliermarsh · 2026-09-11