The best change to my agents setup, for convenience, has been a file reorganization. I no longer choose folders. Instead, I keep a running ledger shared across agents, and available in a single starting point (~/hq for me). A ~10 line agents file tells my agents how to use the ledger to figure out how to find what I'm talking about, and they take it from there.
Every mech interp paper I read seems so obvious and so clear that I wonder how we hadn’t already figured this out. Either that, or interpretability guys are just really skilled at distilling complex concepts into easily understandable foundations. Who would’ve guessed!
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
https://t.co/zHij5zwKGT
Today we're standing up XBOX LABS (https://t.co/dJSufI1vni). Here is the note that I sent to the team:
Team,
The first video games emerged some 75 years ago. In the time since, there have been booms and busts, but every year there are more great games to play, more devices to play them, and best of all, more people than ever playing. That growth helped make XBOX what it is today, and we've helped shape the industry in return, from bringing hard drives to consoles and online gaming through Xbox Live to Game Pass and cloud gaming, alongside franchises that have brought millions of people together.
In recent weeks, we've seen games rapidly decompiled and rebuilt to run on hardware they were never originally designed to support. Windows PC builds have been translated to run on Apple Silicon or ported to run inside a browser through WebAssembly and WebGPU, the latter now approaching 90% global browser support. Perhaps more surprisingly, we've seen many of the biggest games in the world have been remixed into the source code of another.
These experiments challenge long-held assumptions about our industry: the tether between software and hardware, the boundary between creation and play, and how people discover and experience games. While it is hard to predict the future of gaming, it is easy to see the possibilities in making great games easier to access, giving old games new life and allowing more players to become creators and co-creators. These are unmistakably good outcomes for players, even when (and sometimes because) they challenge our existing business models.
To explore these possibilities, I’ve asked Scott to stand-up XBOX LABS, a small group of game makers, engineers and scientists whose job is to turn emerging ideas into things our players and developers can experience. We'll build in the open, learn from what people do, and measure success by whether more people are playing and creating.
I think XBOX has an important role to play here. Coding became the first major workload for agents because they can write, run, and test software. Games share many of those same properties, and people spend more than 72 billion hours a year playing XBOX games, roughly five times the estimated time spent writing code worldwide. We've spent 25 years learning how to make great games, and I want our game makers to help shape what these new technologies make possible. As we learn, we’ll share the tools we build with developers across the industry, just as we always have.
Our priorities aren't changing. We remain committed to the 4Cs, to making great games, to our hardware and to being responsible stewards of IP and the communities built around it. LABS gives us a way to explore new technology that is game design led without abandoning the work already underway.
Asha
Physician compensation versus lifestyle balance (a composite index by Marit that accounts for weekly hours, long shift or after-hours work, call burden, and vacation weeks) by major specialty
The best way to make it through a surgery clerkship is to imagine yourself as Batman. Driving in the dark. Wandering barren halls. Repairing hernias. All to save Gotham
The setup I want:
- Always-on Mac at home
- Coding agent with computer use
- MacBook that syncs my sessions
- iOS app + voice agent paired with my Mac
So I can voice control everything on my machine through the mobile app
And work on those same session when I’m at my desk
Math deals with platonic ideals. LLMs, who carry proto-instantations of these ideals as beings in meaning-space, are naturally suited to its manipulation and traversal
We’re releasing a broad range of new mathematical results produced by an internal frontier model.
We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence at the Institute for Advanced Study, and we have drawn on their advice and public recommendations to inform how we release these results.
https://t.co/7N6TPlft1P
The most practical skill I’ve learned in med school is just saying “tell me more”. It’s magical in conversations. Dates. Small talk. Big talk. 5 minute windows to impress someone. I abuse “tell me more about that” and it feels unfair how well it works
@shahman28 analyze the last 2 years worth of hinge messages. rank my top three offputting features and create proactive agentic workflows to address these shortcomings. use subagents. /goal find me a dermatologist wife willing to subsidize the cost of my failed entrepreneurial ventures
@Bibimboppoo Part time in medicine usually means working the same 40 hour week that anyone else does. 80 hour weeks shouldn’t be a reality in residency, much less an attending’s life