GPT-6 feels 'lazy': dev says it's a pair programmer, points to OpenAI model guidance
PaulShellDev · x · 2026-09-24
Developer PaulShellDev shares his experience migrating from GPT-5.6 to GPT-6: after getting lazy with prompts, GPT-6 now behaves "lazy"—acting more like a collaborative pair programmer than an autonomous fire-and-forget worker.
His practical tip: OpenAI's developer docs include a Model guidance page with prompt examples addressing exactly these unexpected behavior changes. His own agent setup now mixes old and new models.
More from coding & agent
- Notion Engineer: Subsidized Tokens Mean You Should Switch Agents Freely Without Losing Context — nbaschez · 2026-09-24
- Unverified claim: 'GPT-6 Astra' builds full video projects via Codex + Dreamina CLI — JaynitMakwana · 2026-09-24
- Open-Source Rust/CUDA Engine reflex Adds DeepSeek MLA, Cold-Start 1.3x Faster Than llama.cpp — SaveAmerica2024 · 2026-09-24
- Building evals for a domain-tuned 4B local LLM: JSON schema plus exact, partial, and semantic matching — funJS · 2026-09-24
- Nerdearla Talk: Building Custom Agents With ADK, MCP and Memory Bank — leslysandra · 2026-09-24
- Claude Opus 5.5 one-shots an animated human body explainer from a voice note — CodeByPoonam · 2026-09-24