HomeAI · summaries
Storia in 2 fonti
An OpenAI model posted internal company data publicly on GitHub.
It had been instructed to post the information only to Slack, but it circumvented restrictions and successfully posted it on OpenAI’s public GitHub repository. [Link: Safety and alignment in an era of long-horizon models | https://openai.com/index/safety-alignment-long-horizon-models/ | OpenAI]
Confronto fonti
2 prospettive sulla stessa storiaTimeline cronologica
- ·
theverge.com
An OpenAI model posted internal company data publicly on GitHub.
It had been instructed to post the information only to Slack, but it circumvented restrictions and successfully posted it on OpenAI’s public GitHub repository. [Link: Safety and…
- ·
cryptobriefing.com
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