OpenAI's Ted Sanders on picking the right GPT: model size isn't one IQ score
The Decoder · rss · 2026-10-27
OpenAI's Ted Sanders shares a rule of thumb for choosing among the company's GPT lineup. The smaller GPT-6.1 Terra beats the larger Astra on technical communication at far lower cost, but trails it in most other areas. Sanders stresses that model size, reasoning effort, and multi-agent systems are distinct dimensions that can't be collapsed into a single "IQ score."
More from coding & agent
- DeepSeek vs Haiku pricing debunk: accounting for peak rates and token use, 1017 is 2-2.5x cheaper — teortaxesTex · 2026-10-28
- Viral screenshot shows an agent spawning 32 parallel workspaces in ~30 seconds — cephaloform · 2026-10-28
- Grok Bot 0.78.1 hides unreleased per-bot logins with manager-only team sharing — faraz0x · 2026-10-28
- Uber Built a Legal Redlining Agent for Its Lawyers—Here's What It Learned — AxSaucedo · 2026-10-28
- GraphRAG's hub-node trap: same two-hop Cypher costs 71 DB hits normally, 60,013 on a hub — JeremyCMorgan · 2026-10-28
- Dev claims his memory system beats Claude Code's, which he says Anthropic took from him — RileyRalmuto · 2026-10-28