Claude’s new model is more ‘honest’ when it messes up
[RSS: www.theverge.com] Anthropic is releasing Claude Opus 4.8 on Thursday, and the company is touting the model's "honesty." According to Anthropic, it trains "all [its] models to be honest - for instance, to avoid making claims that they can't support." But it notes that...
[RSS: www.theverge.com] Anthropic is releasing Claude Opus 4.8 on Thursday, and the company is touting the model's "honesty." According to Anthropic, it trains "all [its] models to be honest - for instance, to avoid making claims that they can't support." But it notes that...
Anthropic is releasing Claude Opus 4.8 on Thursday, and the company is touting the model's "honesty."
Support Atomni
Help us keep delivering high-quality, independent journalism. Your support makes a difference.
Support Our WorkAccording to Anthropic, it trains "all [its] models to be honest - for instance, to avoid making claims that they can't support." But it notes that "a general problem with AI models is that they sometimes jump to conclusions, confidently presenting their work as making progress despite thin evidence."
The AI lab claims that early testers have found that Opus 4.8 "is more likely to flag uncertainties about its work and less likely to make unsupported claims." In the company's evaluations, Opus 4.8 is "around 4x less likely than its predeces …
Atomni Editorial Desk
Editorial Desk
Comments (0)
No comments yet. Be the first to share your thoughts!