Codex Trio Collaborates on Math Engineering
ChrSzegedy · x · 2026-07-14
In a math engineering project running for 3 weeks, Codex is primarily used as the executor. By adding a review/inspection model named Fable, the author has established a three-model collaboration: Codex, Fable, and GPT Pro Sol.
He states that this combination is helping them push the classification of finite semigroups (within order 7) toward the "optimal path," calling it "true agentic mathematical engineering." The author also mentions investing significant effort into this scaffold and utilizing university infrastructure, with more details to be disclosed later.
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22