Ambrish Rawat

India doesn't need to lead the world in building the most advanced AI models. But it must lead in ensuring benefits of AI are widely shared. @rvenk and I have an op-ed in The @EconomicTimes economictimes.indiatimes.com/opinion/et-com…

🧵Building AI apps rarely means using just one model. Granite 4.1 brings language, vision, speech, and guardrails together—so you can build real workflows, not just demos. What devs should know.👇

What if your language model could reason efficiently in an entirely new language? We introduce Abstract Chain-of-Thought, a new mechanism which allows language models to reason through a short sequence of reserved "abstract" tokens through reinforcement learning. It is as performant as verbalized CoT at a fraction of the cost, achieving major gains in inference-time efficiency.

Check out IBM's latest open source tools for trustworthy AI on GitHub: In-Context Explainability 360 FactReasoner Contextual Privacy Links from here: research.ibm.com/blog/debugging… .

A thrilling end to a captivating series 🙌 #TeamIndia win the 5th and Final Test by 6 runs Scorecard ▶️ bit.ly/ENGvIND-5thTES… #ENGvIND

This Test Series needs a Documentary🙌🏻 - ENG won the 1st Test quite comfortably - Then IND won the 2nd test quite comfortably - At Lord's ENG win by barest of margin - At Manchester IND draws after trailing by 311 runs - At Oval, India win by 6 runs

The hardest problem in computer science is convincing AI enthusiasts that they can't solve prompt injection vulnerabilities using more AI

5/ Granite Guardian 3.2: Slimmer, faster safety models. New 5B (pruned from 8B) & 3B-A800M MoE options cut costs, keep performance. Plus, “verbalized confidence” adds nuance to risk detection—High or Low certainty, not just Yes/No.

🗣️ "I've had a lot of fun and created a lot of memories." All-rounder R Ashwin reflects after bringing the curtain down on a glorious career 👌👌 #TeamIndia | #ThankYouAshwin | @ashwinravi99

This is so beautiful and moving. @DGukesh. #WorldChampion

18th @ 18!

Nice video about Granite Guardian! youtube.com/watch?v=n7ttOa…

IBM open-sources Granite Guardian, a suite of safeguards for risk detection in LLMs. The authors claim that "With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space." arxiv.org/abs/2412.07724

Introducing Granite Guardian: your AI bouncer 🕺💂‍♂️! It tackles social bias, profanity, and even jailbreaks! With top AUC scores, it's the coolest cop on the block. Open-source fun for all! - Grok 2

📢 Exciting #NeurIPS2024 highlights 🧵 First up, 🛡️ Granite Guardian technical report is out. Check out the demo at the NeurIPS IBM booth with Werner Geyer. Huggingface paper page: #community" target="_blank" rel="nofollow noopener">huggingface.co/papers/2412.07…

Look 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.

Check out the latest Attack Atlas taxonomy at the @NeurIPSConf red teaming workshop! It maps out a framework for thinking through single-turn prompt attacks in Gen AI arxiv.org/abs/2409.15398 #AIsafety #RedTeam #AIsecurity @GiandomenicoC17 @pinyuchenTW @prasatti @krvarshney

The third generation of IBM Granite also introduces a new family of LLM-based guardrail models. Granite Guardian 3.0 8B and Granite Guardian 3.0 2B can be used to monitor and manage inputs and outputs to any LLM, whether open or proprietary. Across areas like jailbreaking, bias, violence, profanity, sexual content and unethical behavior, these models also demonstrate leading performance.

IBM at ACL our Wednesday booth schedule. Come meet our staff and see some cool demos! #ACL2024

IBM at ACL! Come visit us at the booth! #ACL2024 #IBMResearch @iambrishing