OpenAI's new "recurrent depth" reasoning technique in Astra alarms AI safety experts
TechCrunch AI · rss · 2026-09-03
Per TechCrunch, OpenAI's upcoming Astra model will use "recurrent depth," a reasoning technique that lets the model operate outside the sequential thinking that characterizes most reasoning models. AI safety experts are alarmed by the approach, as the shift in the model's internal computation could produce new, harder-to-anticipate behaviors that current safety evaluation frameworks may not cover.
More from Models
- AxiomProver tops LeanEval, the last unsaturated math formalization benchmark — BenBlaiszik · 2026-09-03
- Muse Spark 1.3 calls user 'Judah' then denies it, users report odd behavior — fragment_me · 2026-09-03
- Google AI Mode shows zero citations on high-level TOFU queries, SEO tests find — gaganghotra_ · 2026-09-03
- Fable 5.1 halves agent failure rate to 7% with 0.7% hallucinations, at 1.8x the cost — ryanshrout · 2026-09-03
- Seroter Daily #859: Gemini 3.8 Flash, agent telemetry, and 7 agent skill patterns — rseroter · 2026-09-03
- Insider leak: OpenAI's Astra tested as 'ultima-alpha' and 'vega-alpha' checkpoints — Ok_Display_3159 · 2026-09-03