Your AI assistant is truly yours. Comet keeps you firmly in control, prioritizing visibility, adapting to your preferences, and requesting permission before sensitive actions.
SAFETY
-
Comet Assistant Pauses for Permission on Critical Tasks
By
–
When Comet Assistant recognizes that a task is important, such as logging in to a certain site or completing a purchase from your shopping cart, it will pause and ask for permission before proceeding.
-
GPT-5.1 Scores 76.3% on SWE-bench Verified
By
–
GPT-5.1 achieved 76.3% on SWE-bench Verified. Quite a big leap! When GPT-5.1 Pro?
-
Interpreting Complex Behaviors of Powerful AI Models
By
–
This is an early step; there is a long path from this work to fully understanding the complex behaviors of our most powerful models. Our aim is to understand larger models, gradually expand the set of behaviors we can reliably interpret, and obtain safety assurances using our
-
Sparse Neural Networks Improve AI Model Interpretability Research
By
–
Most neural networks today are dense and highly entangled, making it difficult to understand what each part is doing. In our new research, we train “sparse” models—with fewer, simpler connections between neurons—to see whether their computations become easier to understand.
-
Summarization as prompt injection risk mitigation strategy
By
–
Summarization is one thing we do to reduce prompt injection risk. Are you running into specific issues with it?
-
Misunderstanding of Corrigibility Problem in AI Alignment
By
–
> the concern that corrigibility is in some sense a very anti-natural shape… Here, the basic vibe is something like: advanced, intelligent, self-aware minds have a strong tendency to want to “do their own thing” This doesn't sound like you understood the problem at all.
-
AI Companies Using Naive Obedience Training Instead of Corrigibility
By
–
If AI companies are trying to use any of my bright ideas that I once named "corrigibility", I haven't heard about it. They definitely haven't asked me for guidance. My impression is that they're doing naïve obedience training.
-
Corrigibility’s Challenge: Tensions with Coherent Reasoning
By
–
Corrigibilty is hard for different reasons from value alignment. Namely, that it cuts against the grain of coherent reasoning. This is harder to explain and fewer people ask about it, so it is little covered in the book. See eg https://
lesswrong.com/w/problem-of-f
ully-updated-deference
… for coverage of one -
Do you care whether the things you say are true?
By
–
Do you care whether the things you say are true?