Mohammed Alshehri

My implementation of the Recursive Language Model (RLM) paper by @a1zhang , Kraska, and @lateinteraction . Key insight: "Treat long context as an external environment, not something to stuff into a context window." Applied to video understanding — instead of encoding 38K frames into a prompt, the agent: → Treats video as an environment → Writes code to explore segments → Uses recursive LLM sub-calls for analysis Tested: 20+ min video, 7 steps, $0.002 Paper: arxiv.org/abs/2512.24601 Code: github.com/mohammed840/RL…

Prime Intellect engineer: "everyone's bragging about a million-token context. here's what they don't tell you. at 256k tokens GPT-5.5 scores 80% on retrieval. push it to a million and it drops to 36%. the model accepts the context, it just can't reason across it. people call it context rot." in a 20-minute talk he explains why bigger context windows won't save your agents. continual learning + training on your own traces + real environments - that's the fix. Watch the talk, then save!

Okay, this is what it looks like after running /goal for eight hours.

Link:arxiv.org/abs/2606.30406

10/10 One of the most interesting findings: a larger teacher is not always a better teacher. Same-origin teachers train smoothly, while a stronger but distributionally different teacher can destabilise or completely collapse distillation. MOPD is a really practical approach for frontier-model teams: train domain experts independently, improve them in parallel, and integrate them into one model without running one massive coupled RL pipeline.

1/10 A really strong new post-training algorithm: MOPD, Multi-Teacher On-Policy Distillation. The goal is simple: combine multiple specialised RL capabilities into one model without losing performance across domains.

infra husband: i was thinking about the water heater me: what's wrong with it infra husband: nothing. we have to keep it that way

I love building benchmarks and eval rubrics

it really is the age of research. so many novel algorithm breakthroughs already this year, from OPSD, to SDFT, to SDPO, to OPSD (the other one)

Adam Brown (@A_G_I_Joe) is back! General relativity is said to be the most beautiful idea the human mind has ever produced. Most of us will never get to fully appreciate its elegance by taking the 20-lecture graduate course Adam taught on it at Stanford. But in the video below, Adam distills the key idea at its heart so clearly and compellingly that even I could keep up lol. At the core of general relativity, Einstein is trying to figure out the principle behind a particular coincidence: that the mass that resists acceleration and the mass that gravity pulls on just happen to be exactly the same. Adam then leads us through the path of insight which Einstein called his “happiest thought.” Then Adam lectures on black holes. First, by showing how even under special relativity you could create a perpetual motion machine if black holes weren't truly black. And then, by explaining why the observations of an infalling observer and a distant bystander to the black hole would be so radically different Adam leads Blueshift, the team at Google DeepMind cracking science and reasoning. Which gave us the opportunity to discuss at the very end how close we are to AIs that could rediscover general relativity from scratch. Stay till the close for some philosophy of science. 0:00:00 – The coincidence that led Einstein to general relativity 0:16:42 – Gravity is a consequence of curved spacetime, not a force 0:31:46 – Why black holes prevent unlimited energy extraction 0:47:12 – Black holes are the ultimate power plants 1:13:50 – What falling into a black hole would actually feel like 1:18:51 – The three ways we know black holes are real 1:24:21 – The first time we saw gravity bend light 1:29:33 – How far can AI get without experimental evidence? Look up Dwarkesh Podcast on YouTube/Spotify to watch. Enjoy!

@menhguin Claude enforcing bedtime by any means necessary.

claude cutting off blood flow to my neck as it tells me to go to sleep

@rezoundous Massive!!!!!

GPT-5.6 Computer Use improvement is really obvious