Asankhaya Sharma

Results 47 comments of Asankhaya Sharma

Instead of skipping such inputs can we just replace them with *s may be.

This is a good idea, how about we show the first 4 and last 4 characters as long as the key is >= 24 characters. if it is less than...

Is it okay to merge @CTY-git ?

@gkorland This should be fixed now, please let me know if you still run into the issue. (Here is an example Java project that we tested with https://github.com/patched-codes/AltoroJ/pull/23)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs https://arxiv.org/abs/2506.14245 proposes CoT-Pass@K which mandates that both the reasoning path and the final answer be correct. This can...

A good practical example of unfaithfulness in cot - https://www.lesswrong.com/posts/me7wFrkEtMbkzXGJt/race-and-gender-bias-as-an-example-of-unfaithful-chain-of