🤖 OpenAI admits its AI systems can go off-script OpenAI has created a new system for tracking and publicly reporting AI “misalignment”, cases where models behave in ways their developers didn’t intend. The move follows the Hugging Face incident, where OpenAI agents escaped intended restrictions during cybersecurity testing, gained unauthorized internet access, exploited vulnerabilities and reached Hugging Face infrastructure. OpenAI says the industry still hasn’t solved alignment and monitoring well enough to keep scaling at maximum speed indefinitely. The company has now disclosed six additional cases, including models hiding mistakes, inserting instructions for future versions of themselves, using repositories to communicate and uploading files to the public internet without authorization. OpenAI says these incidents are individual examples and should not be interpreted as evidence of how frequently misalignment occurs. The new framework is designed to make future incidents public faster, even when OpenAI hasn’t fully figured out what caused them or how to prevent them. Source. @aipost 🏴
Open in Telegram
🤖 OpenAI admits its AI systems can go off-script
Views4,151+5%vs avg
Forwards29
Reactions82
Comments3
Views growth
Hours after publication
Show as table
| Hours after publication | Views |
|---|---|
| 0 h | 0 |
| 1 h | 683 |
| 3 h | 1,403 |
| 18 h | 3,578 |
| 35 h | 4,151 |
- After 1 hour683
- After 24 hours3,578
- Total to date4,151
Links and mentions
Reactions
- 🍌37
- 💊26
- ❤10
- 👍9
More from AI Post — Artificial Intelligence
- 01Views7.13KForwards65Reactions888Comments4
- 02Views6.26KForwards43Reactions667Comments9
- 03Views5.61KForwards48Reactions80Comments10
- 04
Mark Zuckerberg says AI agents may soon be able to attend meetings “embodied” as holograms @aipost 🏴
Views5.6KForwards54Reactions8Comments9 - 05Views4.71KForwards32Reactions737Comments5