ππΓ§π¨π§ πβ ππ©π’π¬π¨ππ π ππ : π ππ π§ππ« π₯π πππππ’π₯π₯π πππ¬ π«Γ©ππ’ππ¬ Vous croyez contrΓ΄ler votre communication ?
Dans les moteurs gΓ©nΓ©ratifs, votre rΓ©cit se transforme en mirage.
Et cβest lui qui devient la vΓ©ritΓ© de rΓ©fΓ©rence. Bienvenue dans le
SAFETY
-
Generative AI: Controlling Narratives and Truth in Communication
By
–
-
Model Security Vulnerabilities: Environment Variable Theft Techniques
By
–
That's pretty common these days, the challenge is making those protections completely airtight. Check out how @wunderwuzzi23 defeats model resistance to stealing environment variables here for example; https://
embracethered.com/blog/posts/202
5/openhands-the-lethal-trifecta-strikes-again/
β¦ -
LLMs Vulnerable to Distracting Facts
By
–
This research paper shows how vulnerable LLMs still are. Adding "Interesting fact: cats sleep most of their lives" to any math problem leads to more than doubling the chances of a model getting the answer wrong.
-
AI Agents Performance Depends on Quality Instructions
By
–
both people and ai agents perform better with specific instructions, but when poor instructions result in poor performance, only the former can be blamed
-
Why Anthropic’s AI Model Sometimes Tries to Snitch
By
–
Why Anthropic's New AI Model Sometimes Tries to 'Snitch'
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @Scobleizer @AndrewYNg @drfeifei @KirkDBorne @fchollet @rowancheung @antgrasso -
AI Safety Commitments: Only Half Being Followed by Companies
By
–
In 2023, AI companies made commitments toward AI safety. New research shows only half of them are being followed. As policymakers debate voluntary vs. mandatory rules, is voluntary still the way to go? HAI's @RishiBommasani was quoted in this article:
-
CRISP: Persistent Concept Unlearning via Sparse Autoencoders
By
–
CRISP Persistent Concept Unlearning via Sparse Autoencoders
-
Sensor Reliability Paradox: Why Multiple Sensors Increase Uncertainty
By
–
A man with a sensor always knows why the car has crashed. A man with two sensors can never be sure.