Can’t agree more… and I do like the AI stuff!
RESEARCH
-
Meta FAIR releases new models, datasets and code details
By
–
More details on all of the new models, datasets and code released by Meta FAIR last week
-
Meta Open Materials 2024: New Open Source Model for Materials Discovery
By
–
New open source release — Meta Open Materials 2024: a new open source model and dataset from Meta FAIR to facilitate inorganic materials discovery. The Open Materials 2024 models deliver results putting them at the top of the MatBench-Discovery leaderboard. They use the
-
Hugging Face: Follow Your Favorite Open-Source AI Organizations
By
–
What's you favorite open-source AI organization? You can now follow them on @huggingface to get notified each time they release a new model, dataset, paper or app! https://t.co/3slR4NXFkS pic.twitter.com/oXsGN9Ol5B
— clem 🤗 (@ClementDelangue) 25 octobre 2024What's you favorite open-source AI organization? You can now follow them on @huggingface to get notified each time they release a new model, dataset, paper or app! https://
huggingface.co/organizations -
Research on AI Steering Methods for Safer Model Outputs
By
–
We hope our preliminary findings inspire further research on steering methods for safer, more reliable model outputs. Read the full research blog for detailed results, insights, and limitations:
-
Feature Steering vs Prompt Engineering: Unexpected Off-Target Effects
By
–
We also compared feature steering with prompt engineering and found some surprising similarities: for example, prompt engineering also showed unexpected off-target effects.
-
Feature Steering Reduces AI Bias Across Nine Social Dimensions
By
–
Finally, we discovered a feature that significantly reduces bias scores across nine social dimensions within the sweet spot. This did come with a slight capability drop, which highlights potential trade-offs in feature steering.
-
AI Gender Bias Mitigation Unexpectedly Increases Age Discrimination
By
–
However, we also observed unexpected "off-target effects". For example, to our surprise, we found that dialing up the "Gender bias awareness" feature also increased age bias.
-
Finding Sweet Spot for Steering Model Social Bias Features
By
–
We found a "steering sweet spot" where feature steering influences model outputs in intuitive ways without significantly degrading the model’s capabilities. Surprisingly, all 29 social bias related features we tested shared the same sweet spot.
-
Feature Steering Controls Social Bias in AI Models
By
–
Next, we found that feature steering can indeed increase or decrease various forms of social biases in targeted ways. For example, dialing up the "Gender bias awareness" feature significantly increased the gender bias scores in our evaluations.