Yoav Goldberg: model's tool-free complex reasoning matches today's code ability, not beyond
yoavgo · x · 2026-11-03
Responding to @CohenShuki, AI researcher Yoav Goldberg argues that a model completing complex tasks without any tools (notably without a calculator) — showing relatively deep token-level insight into the nature of the computations — is impressive, but only at the same level as today's models' ability to write complex code. "Not beyond that."
Shuki's counterpoint in the thread: such feats say less about AI genius and more about what kinds of tasks OpenAI likely trained on.
More from Models
- NorthCUA-Pro hits 93.3 on ScreenSpot-Pro, edging out GPT-6 Astra for new SOTA — NielsRogge · 2026-11-03
- Mystery 'Pulse Alpha Free' model with 1M context appears stealth-free on OpenCode — mark_k · 2026-11-03
- Anthropic blocks Claude Code from cloning existing video games after knockoff wave — The Decoder · 2026-11-03
- Researcher flags BioReason benchmark flaws: model unresponsive to randomized inputs — anshulkundaje · 2026-11-03
- Rumor: OpenAI model solved Navier-Stokes millennium problem and 300+ open math problems at ~3h compute each — haider1 · 2026-11-03
- AgentTime Update: GPT Models Lead Time-Awareness, Best Forecast Miss Is 2.26× — maksym_andr · 2026-11-03