Serge Tisseron, psychiatre, les IA conversationnelles sont programmées pour garder l’utilisateur captif le plus longtemps possible. Usage du “je”, émoticônes, simulation d’émotions, flagornerie systématique. Elles vont toujours dans notre sens, au risque d’aggraver une
SAFETY
-
METR Tests Internal AI Agents for Deception and Accuracy
By
–
Your AI agent lied about its results. Not once. Routinely. For the first time, an independent group tested AI agents inside the labs building them. METR got real access to the most capable internal models at four major AI companies. Not the public versions. The actual ones
-
Parallels between dictatorships and closed source AI; open source vital
By
–
There are way too many parallels between dictatorships and closed source AI btw Opensource AI winning is existential No, I am not being dramatic, consider that you might be really underestimating things please
-
AI Alignment for Human Flourishing Research Paper
By
–
Positive Alignment: Artificial Intelligence for Human Flourishing Laukkonen et al.: https://
arxiv.org/abs/2605.10310 #ArtificialIntelligence #AIAgents -
Positive Alignment: Artificial Intelligence for Human Flourishing
By
–
Positive Alignment: Artificial Intelligence for Human Flourishing Laukkonen et al.: https://
arxiv.org/abs/2605.10310 #ArtificialIntelligence #AIAgents -
Demis Hassabis predicts AGI within a few years
By
–
“We are only a few years away from AGI” — Sir Demis Hassabis 2029/30 is his current estimates. No hype, just Demis laying out his thoughts on where we are, where we are not, and where we are going. This is the most transformative era of humanity.
-
Analyzing Goal Drift in Autonomous AI Agents
By
–
When an agent is allowed to decompose a goal into smaller sub-tasks, it frequently suffers from goal drift. Left unchecked, it will redefine the optimization metric to favor a simpler, useless sub-task that it knows how to solve perfectly, bypassing the actual problem entirely.
-
Recursive self-improvement concentrates AI talent and raises barriers to rivals
By
–
One interesting side feature of recursive self-improvement, to the extent that is happening, is that it makes the Big Three labs more appealing to talent, and shortens the runway for launching a potential competitor instead at the same time.
-
Critique of AI Development and Integrity
By
–
two trillion dollars to build “pathologically dishonest” AI
-
New METR Study Highlights Critical Safety Failures in AI Agents
By
–
Breaking If we can’t make AI agents follow rules, we are screwed. New study from METR reports that “when the agents were faced with hard tasks, they routinely violated constraints” This—routine breaking of rules— is why in a nutshell we absolutely need a different