

✓Working on @tempo.




Forcing Grok Bots in your X DMs is annoying.

None of the labs have nailed the taxonomy for how to work with agents. Chat = quick, 1-off task (but it can handle substantial tasks too) Projects = knowledge work without a gut repo? Code = code first approach likely with a repo? Artifacts / Pages / Spaces = interactive docs? Personal agent as a separate chat? Muse is one core chat and then sub chats (when should I use those?) Grok Bot style messaging inbox for everything might be best abstraction.





A new superhuman Polytopia bot arrives: "PLATO" by @JackYuan35 - 3.2M param CNN + transformer hybrid: 4 conv blocks into 6 attention blocks - Pure self-play PPO, 31B samples - 700 H100-hours on @modal Play here: polyzero.app

Jensen getting pushed out hurts NVDA shareholders (and anyone with index exposure). The winners are whoever gets to invest in the *private* new co and the CCP. Hard to imagine shareholders voting for that.

opportunity for a state's corporate law requiring a full shareholder vote for removing a founder ceo

pre money valuation for Jensen new co? $500B?

I | Introducing expanded identity primitives for MPP - supporting any identity protocol for machine payments


some thoughts on writing software in nov 2026: - it feels like magic - the first 80% is 100x faster - rewriting systems is also 100x faster - opus 5.5 is very good at a lot of things - "deep flow state" is much easier to reach - almost anything can be built in typescript and rust - building secure things is very, very hard the optimization function is how to maximize agents working on goal with the fewest interruptions needed. some things that help: - know where to trust vs guide (and keep retesting) - give them agency like "i'm going to bed, get this done" - if there is a reward function, ask them to hillclimb - the socratic method works wonders - skills and memories can often hinder - asking agents to review themselves still helps - cowriting a plan/spec/invariants helps sometimes managing your own psychology is equally important: - be a lot more ambitious about what you can achieve - avoid dopamine traps / false signals of progress - get good at parallelizing and context switching there are also some things that don't quite work fluidly yet, but will get unlocked in the very near future: - software factory or "find and fix the bugs" - multiplayer agentic workflows - agents managing other agents for high level outcomes - organizational memory