Sherry Tongshuang Wu
@sherrytswu.bsky.social
Assist. Prof at CMU, CS PhD at UW. HCI+AI, map general-purpose models to specific use cases!
Reposted by Sherry Tongshuang Wu
From @cnet.com, @sherrytswu.bsky.social and @maartensap.bsky.social's @sxsw.com takeaways on how to be a smarter AI user:
www.cnet.com/tech/service...
@ltiatcmu.bsky.social @cmuhcii.bsky.social
www.cnet.com/tech/service...
@ltiatcmu.bsky.social @cmuhcii.bsky.social
5 Ways to Stay Smart When Using Gen AI, Explained by Computer Science Professors
The machine is confident. That doesn't mean it's right.
www.cnet.com
March 17, 2025 at 3:05 PM
From @cnet.com, @sherrytswu.bsky.social and @maartensap.bsky.social's @sxsw.com takeaways on how to be a smarter AI user:
www.cnet.com/tech/service...
@ltiatcmu.bsky.social @cmuhcii.bsky.social
www.cnet.com/tech/service...
@ltiatcmu.bsky.social @cmuhcii.bsky.social
Reposted by Sherry Tongshuang Wu
🚨To continuously foster conceptual & technical innovations for a science of AI Evaluation:
An open collaborative community is initiated by Leverhulme Centre for the Future of Intelligence, to adopt and extend our novel methodology.
Join us: kinds-of-intelligence-cfi.github.io/ADELE!
An open collaborative community is initiated by Leverhulme Centre for the Future of Intelligence, to adopt and extend our novel methodology.
Join us: kinds-of-intelligence-cfi.github.io/ADELE!
March 14, 2025 at 3:37 AM
🚨To continuously foster conceptual & technical innovations for a science of AI Evaluation:
An open collaborative community is initiated by Leverhulme Centre for the Future of Intelligence, to adopt and extend our novel methodology.
Join us: kinds-of-intelligence-cfi.github.io/ADELE!
An open collaborative community is initiated by Leverhulme Centre for the Future of Intelligence, to adopt and extend our novel methodology.
Join us: kinds-of-intelligence-cfi.github.io/ADELE!
Reposted by Sherry Tongshuang Wu
Thrilled to unlock AI Evaluation with explanatory and predictive power through general ability scales!
With a new methodology to
-Explain what common benchmarks really measure
-Extract explainable ability profiles of AI systems
-Predict performance for new task instances, in & out-of-distribution
🧵
With a new methodology to
-Explain what common benchmarks really measure
-Extract explainable ability profiles of AI systems
-Predict performance for new task instances, in & out-of-distribution
🧵
March 11, 2025 at 6:12 PM
Thrilled to unlock AI Evaluation with explanatory and predictive power through general ability scales!
With a new methodology to
-Explain what common benchmarks really measure
-Extract explainable ability profiles of AI systems
-Predict performance for new task instances, in & out-of-distribution
🧵
With a new methodology to
-Explain what common benchmarks really measure
-Extract explainable ability profiles of AI systems
-Predict performance for new task instances, in & out-of-distribution
🧵
Reposted by Sherry Tongshuang Wu
If you're in the CS faculty job market, consider joining a NextStarFaculty Slack workspace. It's a space to share information and experiences with each other. I was invited a while ago, but it's currently a quiet space. With more people, it can be a more helpful place. join.slack.com/t/nextstarfa...
Slack
join.slack.com
November 25, 2024 at 3:03 PM
If you're in the CS faculty job market, consider joining a NextStarFaculty Slack workspace. It's a space to share information and experiences with each other. I was invited a while ago, but it's currently a quiet space. With more people, it can be a more helpful place. join.slack.com/t/nextstarfa...