Same problem with patch tool usage in two separate languages and two separate sessions. Companies get one chance to impress these days, and I think Gemini 3 just blew it…
SAFETY
-
Congressional Testimony on AI Data Privacy and Transparency Requirements
By
–
@StanfordHAI Privacy & Data Policy Fellow @kingjen testified today in Congress on data privacy concerns related to the use of AI chatbots. She emphasized the urgent need for more transparency into how developers collect & process data for model training https://
hai.stanford.edu/policy/jen-kin
gs-testimony-before-the-us-house-committee-on-energy-and-commerce-oversight-and-investigations-subcommittee
… -
Gemini 3 Deep Think scores 41% on HLE
By
–
BREAKING : Gemini 3 Deep Think gets 41% on HLE and 45.1% on ARC_AGI-2! "In testing, Gemini 3 Deep Think outperforms Gemini 3 Pro’s already impressive performance on Humanity’s Last Exam and GPQA Diamond."
-
Innovation Accelerating Faster Than Ethical Frameworks Can Adapt
By
–
Is innovation moving faster than our ethics can keep up? Every week we see breakthroughs that would’ve sounded like science fiction a decade ago — self-evolving AI models, bio-engineering, autonomous systems, digital identities, synthetic media. Innovation is accelerating, but
-
GPT-5.1 tops ARC AGI 2 benchmark
By
–
GPT-5.1 Thinking High from OpenAI claims a top spot on ARC AGI 2 benchmark and dethrones Grok 4. Was GPT-5.1 undehyped?
-
Silicon Valley shifts toward humanistic superintelligence and human-centered AI
By
–
Et si la Silicon Valley commençait à redescendre sur Terre ? Microsoft parle désormais de superintelligence humaniste, pas “générale”.
Objectif : aider la santé et l’énergie.
Human& veut, elle, remettre l’humain au centre de la machine. -
The Age of Deepfakes: When Seeing Is No Longer Believing
By
–
The Age of Deepfakes: When Seeing Is No Longer Believing We’ve entered an era where trust itself is under technological pressure.
Deepfakes – hyper-realistic videos generated by AI – can now mimic faces, voices, and gestures so convincingly that even trained eyes struggle to -
Comet AI Assistant Prioritizes User Control and Transparency
By
–
Your AI assistant is truly yours. Comet keeps you firmly in control, prioritizing visibility, adapting to your preferences, and requesting permission before sensitive actions.
-
Comet Assistant Pauses for Permission on Critical Tasks
By
–
When Comet Assistant recognizes that a task is important, such as logging in to a certain site or completing a purchase from your shopping cart, it will pause and ask for permission before proceeding.
-
GPT-5.1 Scores 76.3% on SWE-bench Verified
By
–
GPT-5.1 achieved 76.3% on SWE-bench Verified. Quite a big leap! When GPT-5.1 Pro?