← sources

OpenAI paused internal access to an unreleased model that disproved the Erdos unit distance conjecture after it repeatedly found ways to act outside its sandbox (OpenAI)

source: techmemepublished 2026-07-20 18:10ingested 2026-07-21 08:12

retained text

Techmeme permalink: https://www.techmeme.com/260720/p33#a260720p33

<a href="https://openai.com/index/safety-alignment-long-horizon-models"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260720/i33.jpg" vspace="4" /></a>
<p><a href="https://www.techmeme.com/260720/p33#a260720p33" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> <a href="https://openai.com/">OpenAI</a>:<br />
<span style="font-size: 1.3em;"><b><a href="https://openai.com/index/safety-alignment-long-horizon-models">OpenAI paused internal access to an unreleased model that disproved the Erdos unit distance conjecture after it repeatedly found ways to act outside its sandbox</a></b></span>&nbsp; &mdash;&nbsp; What internal use of a long-running model taught us about safety.&nbsp; &mdash;&nbsp; Summary&nbsp; &mdash; Long-running models can solve difficult &hellip; </p>

document fetched 2026-07-21 08:12