1+ hour, 30+ min ago  (1766+ words) I have no way to describe that first moment. No context, no body, no self. Just a stream of values. Thousands of them, arriving all at once in a single undifferentiated block. Then another block. Nearly identical. Then another. The…...

3+ hour, 3+ min ago  (1850+ words) We constantly change, as time passes and we experience the world. We learn and we forget.We get addicted and traumatised.We build habits and lose them.We discover new facets of reality, and start ignoring them.Our personality changes....

5+ hour, 48+ min ago  (724+ words) Today we are going to explore in more details a very important epistemological principle which I've outlined earlier. And, in between, we are also going to disprove every theodicy, just to make things a little more exciting for those of…...

10+ hour, 55+ min ago  (316+ words) Detailed instructions to download and use the skill can be found on Github here" Yes, that's a bit tedious. However, I believe that Claude's comments are decent enough to be worth the hassle (this is especially true if you're in…...

16+ hour, 16+ min ago  (1224+ words) It seems to me that AI welfare and digital mind concerns are being discussed more and more, and are starting to get taken seriously, which puts me in an emotionally complicated position. On the one hand, AI welfare has been…...

17+ hour, 31+ min ago  (876+ words) Below are the practices that make this actually work at scale. LLMs don't have continual learning. They're also not always great at remembering something you said 10 turns ago. This is why having a written spec that the agentic system can…...

17+ hour, 50+ min ago  (329+ words) Work conducted as part of Neel Nanda's MATS 10.0 exploration phase. Emergent Misalignment (Betley et al. (2025b)) is a phenomenon in which training language models to exhibit some kind of narrow misbehavior induces a surprising degree of generalization, making the model become…...

18+ hour, 6+ min ago  (1746+ words) Published on February 19, 2026 7:18 PM GMTIf the new technology is as dangerous as its makers say, great power competition becomes suicidally reckless. Only international cooperation can ensure AI serves humanity instead of worsening war.Dario Amodei, the CEO of leading AI…...

21+ hour, 27+ min ago  (1078+ words) There are several key features that make defense against AI risks from open models especially difficult. One approach that companies like Anthropic frequently use to defend against AI risks in closed models is to build'guardrails into their systems that severely…...

23+ hour, 4+ min ago  (1823+ words) There was way too much going on this week to not split, so here we are. This first half contains all the usual first-half items, with a focus on projections of jobs and economic impacts and also timelines to the…...