Sergey Karayev tests whether GPT-6 Astra High can one-shot a full GitLab implementation
sergeykarayev · x · 2026-09-17
Sergey Karayev launched an extreme coding test: can GPT-6 Astra High one-shot a full working GitLab implementation? He shares his prompt strategy — telling the model not to message back until 100% complete, then to run 3 independent qa-code-reviews and fix agreed high/medium findings — to stress-test the model's long-horizon autonomous coding.
More from coding & agent
- Codex pro tip: @-mention threads to orchestrate fleets of collaborating agents — paw_lean · 2026-09-17
- Built and launched a data-driven app from a phone using Amp's parallel threads — iannuttall · 2026-09-17
- Perplexity ships Search SDK cookbook: code-controlled search feeds migration briefs to coding agents — AravSrinivas · 2026-09-17
- draw.io joins Claude connector directory, renders editable diagrams inline in chat — msharmas · 2026-09-17
- Dev builds an agent-in-the-middle creative studio: briefs in, interactive prototypes out — jh3yy · 2026-09-17
- Zed founder teases: where are the 'CLI beats MCP' folks now? — zeeg · 2026-09-17