Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 01/04/2025Happy to see Granite Guardian models atop the GuardBench leaderboard, including in non-English languages. This benchmark was just released. Read about it here: www.linkedin.com/posts/eliasb.... 031
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 28/02/2025Four exciting things to share about watsonx.governance and Granite Guardian. Fun times in AI safety! See thread for the details. 111
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 11/01/2025The Chinese translation of my book Trustworthy Machine Learning is now available to be ordered. Here's the JD.COM link: item.jd.com/101351791986.... Congratulations to Prof. Zhao Zheng from Dalian Maritime University for completing it. 031
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 27/12/2024a snippet from mitpress.mit.edu/978026204920... 100
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 18/12/2024We released Granite Guardian 3.1 today! Even better at harm detection than Granite Guardian 3.0. The main new feature is 'function calling hallucination' detection relevant for tool-using AI agents. github.com/ibm-granite/... 071
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 11/12/2024Look at those beautiful Granite Guardian safety vests! #brand #bootleg The Granite Guardian technical report is now on arXiv: arxiv.org/abs/2412.07724 Give it a read to see how the model is state-of-the-art in detecting harmful or hallucinated prompts and responses. 000
Kush Varshney कुश वार्ष्णेय @krvarshney.bsky.social · 10/12/2024It is @neuripsconf.bsky.social booth setup day! Among Ambrish Rawat, @bhoov.bsky.social, and @wernergeyer.bsky.social, who do you think is *not* an author of the Granite Guardian technical report we released today? (Hint: Granite Guardian helps make any LLM safer.) Link: github.com/ibm-granite/... 062