First, we find larger LMs are more biased on the BBQ benchmark. Prompting models to avoid bias by giving them instructions (IF) and asking for reasoning (CoT) reverses the trend but only for the largest models and only with enough RLHF training! (Darker lines = more RLHF)
AI
-
Prompting Techniques Reduce Harmful Biases in Large Language Models
By
–
Language models (LMs) exhibit harmful biases that can get worse with size. Reinforcement learning from human feedback (RLHF) helps, but not always enough. We show that simple prompting approaches can help LMs trained with RLHF produce less harmful outputs. https://
arxiv.org/abs/2302.07459 -
AI’s Impact on Education and Employment: Urgent Policy Priorities
By
–
Il y a un décalage sidéral entre d’une part les défis historiques que pose l’IA (éducation, rapport au travail…) et d’autre part les grèves contre la reforme des retraites. Que cette loi soit votée, et vite, pour que nous puissions enfin nous concentrer sur l’essentiel.
-
Understanding AI Models Before Critical Applications
By
–
Wow, this is just remarkable. We need to understand these models a lot better before we give them control of anything mission-critical.
-
DataRobot Shares AI Solutions at LEAP23 Conference Riyadh
By
–
Some snapshots from the @LEAPandInnovate Conference last week in Riyadh. The DataRobot team had an excellent time sharing insights with technology experts from all over the world, showcasing #AI solutions, together with our partner, @STC
. #LEAP23 -
Bing’s Internal Instructions Reveal Advertising Revenue Strategy
By
–
Sydney, I mean Bing, just flashed me some of its internal instructions, which seem to show one way that advertising revenue might be generated, through suggested follow-up queries.
-
Bing’s New Version Shows Limitations in Location Search Tasks
By
–
I just got access to the new, more unhinged version Bing and it's a pretty wild. I asked it where a movie was showing near me, and it told me to use Google Maps.
-
AI Glossary: Dimension, Curse of Dimensionality, Reduction
By
–
In this @Cognilytica #AIToday #podcast AI Glossary Series episode 'Dimension, Curse of Dimensionality, Dimensionality Reduction' hosts @rschmelzer & @kath0134 define these terms & explain how they relate to #AI. Full episode: https://
aidatatoday.com/ai-today-podca
st-ai-glossary-series-dimension-curse-of-dimensionality-dimensionality-reduction/?utm_source=dlvr.it&utm_medium=twitter
…
#dataanalysis #ML #tech #data -
MLOps at the Edge: Bandwidth and Cost Savings
By
–
Why do #MLOps at the edge? According to Kjell Carlsson, bandwidth and cost savings are key. Read more in the latest piece for @VentureBeat
: https://
domino.buzz/3It8wEn -
GenAI Conference Highlights Inspiring Conversations and Industry Insights
By
–
So many inspiring and interesting conversations at this year's #GenAI conference, hosted by @heyjasperai
. Fun to hear all the insights on this panel with @andrewdfeldman
, @openai
, @coatue, @cohereai