Neuralese explained: why OpenAI's Astra architecture has safety researchers alarmed
ShakeelHashim · x · 2026-09-04
Following a report that OpenAI's new Astra model uses an architecture that could make its reasoning harder to monitor, this explainer covers why chain-of-thought matters for both capability and safety, what 'neuralese' means, and why researcher Ryan Greenblatt called the news possibly 'the single worst development for AI security/safety to date.'
Related event: Researchers Debate Whether Chain-of-Thought Monitoring Can Keep AI Safe(38 posts)→
More from Models
- OpenAI launches GPT-6 Astra, claiming it can do anything you do on a computer — kagigz · 2026-09-04
- Databricks evals: GPT-6 Astra claims SOTA on OfficeQA Pro benchmarks, cheaper per task — downingARK · 2026-09-04
- Mathematician tests GPT-6 Astra: live Lean proof verification while writing arguments — teortaxesTex · 2026-09-04
- Tavus Launches Sparrow-2, Claiming #1 in End-of-Turn Detection and Interruption Handling — ycombinator · 2026-09-04
- ARC-AGI-3: 10x reasoning tokens cuts total cost from $48k to $26k vs medium — i_dg23 · 2026-09-04
- Researchers flag data contamination concerns in benchmark behind Astra's time-horizon score — dfrsrchtwts · 2026-09-04