

Neil Traft
9K posts

@ntraft
PhD student at @uvmcomplexity. Interested in ML, evolution, & self-organization. https://t.co/ja3fdtRLdM






In the last few months, I've spoken to many CS professors who asked me if we even need CS PhD students anymore. Now that we have coding agents, can't professors work directly with agents? My view is that equipping PhD students with coding agents will allow them to do work that is orders of magnitude more impressive than they otherwise could. And they can be *accountable* for their outcomes in a way agents can't (yet). For example, who checks the agent's outputs are correct? Who is responsible for mistakes or errors?









If you, as a CS Prof, are wondering whether you need PhD students at all now that you have wangled a subscription to Claude Code, your lab probably had a pretty depressing vibe to begin with--and 'em students are likely better off with you hanging out with Claude.. #AIAphorisms

Do people become more conservative as they age? If they were born between 1940 and 1954, the answer is clearly "yes." Among people born from 1955 to 1979, there's really been no change. For those born in 1980 or later, it looks they are becoming more liberal as they age.

The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them. Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later. I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run: github.com/karpathy/autor… Alternatively, a PR has the benefit of exact commits: github.com/karpathy/autor… but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back. I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.

You may have noticed some "holy $%@#" tweets on fly brain emulation. So is this a game-changer or a nothing-burger? Read on to find out...










“Software engineering is an unusual discipline. Many people mistake it for simply typing code into an IDE, as if it’s a straightforward translation problem. In reality, software engineering requires specification, architecture, and compositional creativity. You have to design systems, reason about constraints, and break problems into parts before any code is written. Large language models are extremely useful for research and implementation assistance. But when it comes to designing a truly novel solution, something that hasn’t been built before they still struggle. Most of software engineering isn’t typing code. It’s thinking.” Thoughts from Jeremy Howard on the @MLStreetTalk podcast