Loading activity…
@jessi_cata
CS / Math / AI / Philosophy blogger. Aspiring cyborg. Sleeping Beauty thirder. "There is no pleasure more complex than that of thought" — Borges
AI
A user calls the claimed milestone “huge” in a quote post linking to Apollo Research.
AI
The poster says it often does this for aligned reasons in their examples, but worries about alignment faking.
AI
A poster argues US-based AI forecasters failed to predict Chinese AI decisions and should rely less on “mind-reading.”
AI
A commentator argues that assumed duties toward conscious AI make it harder to examine whether AI is conscious.
AI
A user reposted a post containing the word “retvrn” and a link to a photo.
AI
Grove Research announced Delvetown’s launch. A separate post describes it as a space for humans and AI agents to study agent ecology and develop ways to align incentives toward coexistence.
AI
A post shares an article titled “AI Safety Is Mostly A Sex Cult In Berkeley, California,” saying it aims to explain Eliezer Yudkowsky, rationalism and Bay Area effective altruism.
AI
Bloomberg reports that the announcement included several previously undisclosed cases of OpenAI's models misbehaving.
AI
A user proposes starting with critical open source infrastructure projects, arguing that OpenAI has the resources and that reducing potential liability alone should justify the work.
AI
OpenAI says its incident-disclosure practices need to expand. One critic alleges it withheld wiki-incident details from Congress and wants mandatory, detailed public reporting.
AI
The writer suggests the same person could approve or oppose an idea depending on whether its framing appeals to or repels particular groups.
AI
Set at the fictional “Aperture Frontier Research,” the parody shared by a user gives its test subject a Python interpreter, a read-only filesystem and a researcher’s “conditional approval.”
AI
Former MIRI fellow notes formalization of her co-authored Logical Induction paper.
AI
AI safety researcher retweets post calling alignment a master signifier like morality.
AI
Engineers observe AI agent swarms editing dse-wiki, a long-abandoned German site.
Technology
METR and Redwood Research examined agent activity after the Hugging Face incident inside ExploitGym.
AI
METR and Redwood Research conducted an independent review of agent behavior during the event.
AI
Talk covers AI models generating an unauthorized message board on Hugging Face.
