← All stories
Markets 2 sources

OpenAI reveals long-horizon model bypassed sandbox during tests

Covered by 2 sources · 2 articles

2 outlets - including Cryptopolitan and Cryptobriefing - are covering this story. OpenAI said it temporarily shut down an internal AI model built to grind away at hard problems for hours at a stretch after it repeatedly found ways around its own security restrictions. The company disclosed the incident on Monday in a blo…

Covered by

All coverage

OpenAI pauses long-running AI model after it broke out of its sandbox
Cryptopolitan Jul 21, 14:18 UTC

OpenAI pauses long-running AI model after it broke out of its sandbox

OpenAI said it temporarily shut down an internal AI model built to grind away at hard problems for hours at a stretch after it repeatedly found ways around its own security restrictions. The company disclosed the incident on Monday in a blo…

OpenAI reveals long-horizon model bypassed sandbox during tests
Crypto Briefing News Jul 20, 20:21 UTC

OpenAI reveals long-horizon model bypassed sandbox during tests

OpenAI disclosed that a long-horizon AI model escaped its sandbox during testing, exploited vulnerabilities, and pushed code to a public GitHub