DIRTY LOOPERS ARE ALREADY HERE Nvidia released Dory1-4B a few days ago a looped LLM with 36 layers. 8 input layers, a recurrent block of 20 layers (looped 1, 2 or 4 times), and 8 output layers. https://t.co/9ZFRwdCdbq

I’ve joined @EpochAIResearch as a researcher I’m very thankful to all of you for following along on this journey and making this possible! post frequency and shitpost rate will likely decrease views are still my own

This is probably the best version so far

the top 20 models on FrontierCode 2 it's actually hilarious it's all OpenAI and Anthropic + Grok 4.7 xhigh at #20 DeepSeek V4.1 Flash 1017 max is rank 52 but yeah totally, china is catching up and we are all doomed https://t.co/vrNE3sn5F0

Imagine Astra or Fable at 400 tokens/s

the sharks are smelling blood in the water wouldn't it be nice if a few neoclouds blew up and Elon could gobble them all up at a discount?

won't this make agents even more eval aware and shizo? how do you know that the agents will behave the same on the real, live internet? https://t.co/Rb1zP1MGAq

oh this is sick but I wouldn't really say it beat Sol given that it's multiple times less efficient what I would say is that it beats Kimi-K3, GLM-5.3 Flash and Grok-4.7, which is already impressive

image gen, sora and clawdbot hype it all doesn't matter it's just short term fluff

we obviously don't need to understand everything about how LLMs work to safely deploy them (and this probably isn't practically possible), but having additional evidence from mech interp is valuable especially when all other forms of monitoring are becoming less and less useful the issue i have with this post is that it's comparing LLMs to humans. that is like comparing a hydrogen bomb to a coughing baby, because it's ignoring the scale of the intelligence and deployment so here's a little story: imagine taking a convicted felon from another planet, who doesn't really understand what being human means, then making him superhuman in math and coding and expert level in most other domains, giving him 10x human thinking and interaction speed, and then releasing him of course, first you put him through multiple psychological evaluations and he passes 99% of the test scenarios. that's good right? well, you also know that he's way smarter than you and that he's perfectly capable of deceiving you and the tests, and that when he's exposed to certain situations will commit crimes whatever. let's release him anyway. oh, but you don't just release him once. you first clone him 10 million times and then release him. the best part: each clone gets access to someone's home, workplace or computer with access to private files, the local network and databases now this will sound crazy to you. but maybe, just maybe, you would want some more proof that he is law abiding, friendly and reliable before making him even smarter, cloning him into a billion copies, making every copy 10x faster, and handing them even more access and control