Nope too much for me Not natural behavior imho
SAFETY
-
Anthropic Demonstrates Internal Feature Modification in Claude AI
By
–
This week, we showed how altering internal "features" in our AI, Claude, could change its behavior. We found a feature that can make Claude focus intensely on the Golden Gate Bridge. Now, for a limited time, you can chat with Golden Gate Claude: http://
claude.ai -
Programmatic AI Development for LLM Policy Alignment and Superalignment
By
–
Learn how programmatic AI data development techniques enable enterprises to align LLMs to their specific policies and objectives and embark on the path toward superalignment.
-
Seoul AI Safety Summit: A Historic Step Toward Accountability and Transparency?
By
–
[#Article] Seoul AI Safety Summit: A historic step toward accountability and transparency? https://actuia.com/actualite/ai-safety-summit-de-seoul-un-pas-historique-vers-la-responsabilite-et-la-transparence/
… #AI #ArtificialIntelligence -
French DeepMind Alums Raise $220M for Safe AGI
By
–
Holistic AI, a french startups, comes out with a $220m round bang (yes, they are DeepMind alums). It's a safety and governance focused startup going for 'Full AGI': https://
pymnts.com/artificial-int
elligence-2/2024/ai-startup-h-raises-220-million-for-full-agi/
… their message is basically… "an AGI company that won't make you sick and kill you!" -
Pope Francis Critiques Techno-Utopianism Environmental Protection
By
–
In Rome for a meeting and Pope Francis is here! Huge fan of his Laudate Si and Laudate Deum, esp his strong take against techno-Utopianism and for protecting the planet.
-
Anthropic’s interpretability team delivers impressive research work
By
–
Some really nice work by Anthropic's interpretability team. Kudos to @ch402 (former intern!) and everyone else involved!
-
Resources on AI assistants problems and research insights
By
–
You can read more in our article here: https://
catalystjournal.org/index.php/cata
lyst/article/view/29949/26063
…
And here's an important article from DeepMind on the problems with AI assistants: https://
drive.google.com/file/d/13mLAeN
TL7TbscYuGdEXTFHemWGd7HLhn/view
…
