What Should We Take From Anthropic’s (possibly) Terrifying New Report on Mythos? – @garymarcus’s latest @CACMmag cacm.acm.org/blogcacm/what-s…
ETHICS
-
Reflecting on the challenges of LLM alignment through analogies
By
–
"There is substantial overlap between the smartest bears and the least-equipped humans" was once an observation on how it is difficult to engineer a bear-proof garbage receptacle for national parks. I think a spiritually similar thing happens with LLMs.
-
Methodologies for Reducing Errors in AI Systems
By
–
Some approaches:
1) Multiple reviews. Some papers already show having many AI team members review a problem reduces errors
2) Building in tests and checkpoints 3) Multiple independent answers that are cross-checked
4) Clear processes that escalate to smarter systems for review -
Applying organizational risk management structures to mitigate AI hallucinations
By
–
Hallucinations remain in LLMs, but note that over centuries we have developed complicated, successful machines that take uncertain output from unreliable sources & reduce the risk of errors. We call those machines organizational structures & we can apply similar approaches to AI
-
Political opposition to AI and ethical concerns about intelligence technology
By
–
Also, when reality hits, the people who have never used it and see no utility in Intelligence, will easily fall into the AOC/Sanders camp of ‘this is evil billionaire stuff and must be stopped’ camp I suspect. The ‘Demis version’ of we will cure all disease doesn’t seem to be
-
Weak Arguments About AI: Intellectual Exercise and Critique
By
–
Dudes who won’t tag me because they know their arguments are weak sauce.*
— Gary Marcus (@GaryMarcus) 8 avril 2026
*for intellectual exercise you can list the flaws and misrepresentations in his argument below pic.twitter.com/gYqiFeUBMDDudes who won’t tag me because they know their arguments are weak sauce.* *for intellectual exercise you can list the flaws and misrepresentations in his argument below
-
OpenAI Withholds Full Algorithm for New Text Generation Model
By
–
"Last week, the nonprofit research group OpenAI revealed that it had developed a new text-generation model that can write coherent, versatile prose given a certain subject matter prompt. However, the organization said, it would not be releasing the full algorithm due to “safety
-
GPT-2 Safety Debate: 2019 Warnings Revisited Today
By
–
There's a few people out there who have seen the current day narrative repeated over and over again… I present to you an article from 2019 that describes why GPT-2 is too dangerous to release to the public.
-
AI Regulation: American Legislative Chaos of 2026
By
–
Congress has debated federal AI regulation for 3 years. No law passed.45 states got tired of waiting. 1,561 AI bills introduced in 2026 alone.Not one of them sets safety standards or capability limits on actual AI systems. [Translated from EN to English]
→ View original post on X — @scobleizer, 2026-04-08 18:30 UTC
-
Claude Mythos Delusional: Critical Analysis Video
By
–
I agree with everything in this video. 10/10. No notes. https://t.co/YoAxsWsBen
— Adam Jacob (@adamhjk) 8 avril 2026I agree with everything in this video. 10/10. No notes. Mo (@atmoio) Claude Mythos is Delusional — https://nitter.net/atmoio/status/2041935999945625745#m