Michael Hind
@michaelhind.bsky.social
IBM Distinguished RSM, working on AI transparency, governance, explainability, and fairness. Proud husband & dad, Soccer lover. Posts are my own.
Pinned
Michael Hind
@michaelhind.bsky.social
· Apr 15
IBM enhances the capabilities of watsonx.governance with the new Model Risk Evaluation Engine
We're excited to announce the Model Risk Evaluation Engine, a new tool in watsonx.governance that can measure measures risks of foundation models by computing metrics related to risk dimensions from t...
www.ibm.com
Are you wondering how you can evaluate some of the risks of a foundation model before you deploy it? Read on .... www.ibm.com/new/announce...
An interesting backstory of a common test photo sparked another photo (of @krvarshney.bsky.social) in another dataset. research.ibm.com/blog/kush-va...
How IBM’s Kush Varshney became an iconic ’test’ photo
The IBM Fellow reflects on copyright law, generative AI, and how he became the face of the modern camera man
research.ibm.com
July 21, 2025 at 6:17 PM
An interesting backstory of a common test photo sparked another photo (of @krvarshney.bsky.social) in another dataset. research.ibm.com/blog/kush-va...
I'm excited to be a part of this great collaboration with colleagues at IBM Research and Notre Dame. lucyinstitute.nd.edu/news-events/...
University of Notre Dame and IBM Research build tools for AI governance - Lucy Family Institute for Data & Society
Expanding into virtually all aspects of modern society, AI systems are transforming everything from education to healthcare, but how trustworthy are the vast
lucyinstitute.nd.edu
July 17, 2025 at 1:27 PM
I'm excited to be a part of this great collaboration with colleagues at IBM Research and Notre Dame. lucyinstitute.nd.edu/news-events/...
Are you wondering how you can evaluate some of the risks of a foundation model before you deploy it? Read on .... www.ibm.com/new/announce...
IBM enhances the capabilities of watsonx.governance with the new Model Risk Evaluation Engine
We're excited to announce the Model Risk Evaluation Engine, a new tool in watsonx.governance that can measure measures risks of foundation models by computing metrics related to risk dimensions from t...
www.ibm.com
April 15, 2025 at 4:14 PM
Are you wondering how you can evaluate some of the risks of a foundation model before you deploy it? Read on .... www.ibm.com/new/announce...
Reposted by Michael Hind
I'm on the IBM Mixture of Experts podcast wearing a safety vest. We talk about all the new things in AI this week. I also connect to older work by IBM Fellows Irene Greif, Bob Dennard, Rolf Landauer, and Charlie Bennett and to Mauro Martino's new AI-generated film. www.youtube.com/watch?v=CgqH...
DeepSeek-V3-0324, Gemini Canvas and GPT-4o image generation
YouTube video by IBM Technology
www.youtube.com
March 28, 2025 at 1:10 PM
I'm on the IBM Mixture of Experts podcast wearing a safety vest. We talk about all the new things in AI this week. I also connect to older work by IBM Fellows Irene Greif, Bob Dennard, Rolf Landauer, and Charlie Bennett and to Mauro Martino's new AI-generated film. www.youtube.com/watch?v=CgqH...
Reposted by Michael Hind
Happy 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....
This benchmark was just released. Read about it here: www.linkedin.com/posts/eliasb....
April 1, 2025 at 7:31 PM
Happy 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....
This benchmark was just released. Read about it here: www.linkedin.com/posts/eliasb....
Reposted by Michael Hind
A summary of decolonial AI alignment in the Human-Centered AI publication on Medium. Thanks to @jweisz3.bsky.social for asking me to write it, and for editing the piece. medium.com/human-center...
Decolonial AI Alignment
by Kush Varshney (IBM Research, US)
medium.com
April 8, 2025 at 3:12 PM
A summary of decolonial AI alignment in the Human-Centered AI publication on Medium. Thanks to @jweisz3.bsky.social for asking me to write it, and for editing the piece. medium.com/human-center...
I'm happy to see my former IBM colleague raise this important issue regarding Agentic systems. www.linkedin.com/posts/thomas...
Work for me, but don’t pretend to be me: on transparency of identity in AI… | Thomas Hampp
You may trust your concierge with the keys to your house, but would you allow them to sign with your name? What about giving your AI agent the API keys to your accounts?
In my article, I discuss an i...
www.linkedin.com
April 9, 2025 at 3:43 PM
I'm happy to see my former IBM colleague raise this important issue regarding Agentic systems. www.linkedin.com/posts/thomas...
From Erik Miehling (www.linkedin.com/posts/erik-m...)
"AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation of the true capabilities and associated risks of agentic AI."
"AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation of the true capabilities and associated risks of agentic AI."
Erik Miehling on LinkedIn: AI development is currently overly focused on individual model…
AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation…
www.linkedin.com
March 5, 2025 at 12:08 AM
From Erik Miehling (www.linkedin.com/posts/erik-m...)
"AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation of the true capabilities and associated risks of agentic AI."
"AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation of the true capabilities and associated risks of agentic AI."
Reposted by Michael Hind
Four exciting things to share about watsonx.governance and Granite Guardian. Fun times in AI safety! See thread for the details.
February 28, 2025 at 9:29 PM
Four exciting things to share about watsonx.governance and Granite Guardian. Fun times in AI safety! See thread for the details.
From Elizabeth Daly: "This week we are releasing, Risk Atlas Nexus, github.com/IBM/risk-atl..., an open source project that provides tooling to help bring together disparate resources related to governance of foundation models. ... "
February 28, 2025 at 8:32 PM
From Elizabeth Daly: "This week we are releasing, Risk Atlas Nexus, github.com/IBM/risk-atl..., an open source project that provides tooling to help bring together disparate resources related to governance of foundation models. ... "
Reposted by Michael Hind
"While techniques such as the ones used by R1 can degrade model safety, our preview release shows that reasoning and safety don’t have to be a trade-off."
www.ibm.com/new/announce...
www.ibm.com/new/announce...
Bringing reasoning to Granite
We’re excited to announce a preview release of new reasoning capabilities in our Granite family of large language models.
www.ibm.com
February 8, 2025 at 8:11 PM
"While techniques such as the ones used by R1 can degrade model safety, our preview release shows that reasoning and safety don’t have to be a trade-off."
www.ibm.com/new/announce...
www.ibm.com/new/announce...
It was a pleasure to join the panel discussion on Humanitarian AI Today podcast below, moderated by Brent Phillips: podcasts.apple.com/us/podcast/t...
Transparency in Discussion: Improving Transparency and Accountability in AI Implementations
Podcast Episode · Humanitarian AI Today · 11/24/2024 · 1h 19m
podcasts.apple.com
December 23, 2024 at 5:03 PM
It was a pleasure to join the panel discussion on Humanitarian AI Today podcast below, moderated by Brent Phillips: podcasts.apple.com/us/podcast/t...
Reposted by Michael Hind
"IBM has equipped the Granite Guardian 3.1 models with the ability to detect hallucinations in AI agent workflows. This feature provides oversight of an AI agent completing a task, monitoring for fabricated information or incorrect function calls." technologymagazine.com/articles/the...
The Key to How IBM's Granite 3.1 is Advancing Enterprise AI
IBM’s new Granite 3.1 addresses key enterprise needs, including expanded context handling, multilingual support, new tools and AI agent development
technologymagazine.com
December 20, 2024 at 9:27 PM
"IBM has equipped the Granite Guardian 3.1 models with the ability to detect hallucinations in AI agent workflows. This feature provides oversight of an AI agent completing a task, monitoring for fabricated information or incorrect function calls." technologymagazine.com/articles/the...
Reposted by Michael Hind
Reminder: The #FAccT2025 submission deadlines are roughly one month away! Abstracts are due January 15th and full papers on January 22nd. See the full CfP here: facctconference.org/2025/cfp
ACM FAccT - 2025 CFP
facctconference.org
December 17, 2024 at 8:24 PM
Reminder: The #FAccT2025 submission deadlines are roughly one month away! Abstracts are due January 15th and full papers on January 22nd. See the full CfP here: facctconference.org/2025/cfp
Reposted by Michael Hind
I showed this cool demo last week @neuripsconf.bsky.social Now we have a public version on Hugging Face that you can play with to see the "judge" model in action. huggingface.co/spaces/ibm-g...
Enjoy!
Open source repo & benchmarks: github.com/ibm-granite/...
Enjoy!
Open source repo & benchmarks: github.com/ibm-granite/...
Granite Guardian Demo - a Hugging Face Space by ibm-granite
demo
huggingface.co
December 16, 2024 at 10:22 PM
I showed this cool demo last week @neuripsconf.bsky.social Now we have a public version on Hugging Face that you can play with to see the "judge" model in action. huggingface.co/spaces/ibm-g...
Enjoy!
Open source repo & benchmarks: github.com/ibm-granite/...
Enjoy!
Open source repo & benchmarks: github.com/ibm-granite/...
Reposted by Michael Hind
Now posted at the under construction booth 😀 our demo lineup for Tuesday. Looking forward connecting with you at the IBM booth @neuripsconf.bsky.social
December 9, 2024 at 11:24 PM
Now posted at the under construction booth 😀 our demo lineup for Tuesday. Looking forward connecting with you at the IBM booth @neuripsconf.bsky.social
Reposted by Michael Hind
It 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/...
Link: github.com/ibm-granite/...
December 10, 2024 at 12:27 AM
It 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/...
Link: github.com/ibm-granite/...
Reposted by Michael Hind
If you’re headed to NeurIPS 2024, and want to learn about IBM Research Human-Centered Trustworthy AI, there are many many opportunities to do so.
1. Start with the official NeurIPS explorer by @henstr.bsky.social and @benhoover.bsky.social. It is infoviz par excellence. neurips2024.vizhub.ai
1. Start with the official NeurIPS explorer by @henstr.bsky.social and @benhoover.bsky.social. It is infoviz par excellence. neurips2024.vizhub.ai
Tips
neurips2024.vizhub.ai
December 7, 2024 at 2:50 AM
If you’re headed to NeurIPS 2024, and want to learn about IBM Research Human-Centered Trustworthy AI, there are many many opportunities to do so.
1. Start with the official NeurIPS explorer by @henstr.bsky.social and @benhoover.bsky.social. It is infoviz par excellence. neurips2024.vizhub.ai
1. Start with the official NeurIPS explorer by @henstr.bsky.social and @benhoover.bsky.social. It is infoviz par excellence. neurips2024.vizhub.ai
I'm happy to announce a significant revision of our paper describing opportunities and challenges of quantitative AI risk assessments, also known as automated red-teaming: arxiv.org/abs/2209.06317
Quantitative AI Risk Assessments: Opportunities and Challenges
Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have...
arxiv.org
December 7, 2024 at 2:25 AM
I'm happy to announce a significant revision of our paper describing opportunities and challenges of quantitative AI risk assessments, also known as automated red-teaming: arxiv.org/abs/2209.06317
Reposted by Michael Hind
🎺 Here comes the official 2024 NeurIPS paper browser:
- browse all NeurIPS papers in a visual way
- select clusters of interest and get cluster summary
- ZOOOOM in
- filter by human assigned keywords
- filter by substring (authors, titles)
neurips2024.vizhub.ai
#neurips by IBM Research Cambridge
- browse all NeurIPS papers in a visual way
- select clusters of interest and get cluster summary
- ZOOOOM in
- filter by human assigned keywords
- filter by substring (authors, titles)
neurips2024.vizhub.ai
#neurips by IBM Research Cambridge
December 3, 2024 at 5:01 PM
🎺 Here comes the official 2024 NeurIPS paper browser:
- browse all NeurIPS papers in a visual way
- select clusters of interest and get cluster summary
- ZOOOOM in
- filter by human assigned keywords
- filter by substring (authors, titles)
neurips2024.vizhub.ai
#neurips by IBM Research Cambridge
- browse all NeurIPS papers in a visual way
- select clusters of interest and get cluster summary
- ZOOOOM in
- filter by human assigned keywords
- filter by substring (authors, titles)
neurips2024.vizhub.ai
#neurips by IBM Research Cambridge
I enjoyed my recent interview on the AI Risk Reward podcast with host Alec Crawford.
You can hear it here: podcasts.apple.com/us/podcast/t...
You can hear it here: podcasts.apple.com/us/podcast/t...
March 20, 2024 at 12:22 PM
I enjoyed my recent interview on the AI Risk Reward podcast with host Alec Crawford.
You can hear it here: podcasts.apple.com/us/podcast/t...
You can hear it here: podcasts.apple.com/us/podcast/t...