Hamid Khan Tabi
2.4K posts
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.
Spark is now intelligent you can now leave Spark on full autonomous learning on any skill, and it will improve constantly > it will loop all day, infinitely, in anything you direct it for self-improvement > research and understand patterns in that main area > grow its skills there > even mutate learnings to cross-domain skills > and go through AI inference models with the insights it gathered to train its own understanding and reasoning capabilities this alpha is not out yet, but I can finally say that we achieved the foundation that I was dreaming of when I began to work on Spark will show all of this live, on a stream on Sunday and then prepare to release the recursive self-improving alpha version Here are snippets from this morning, after it analyzed YC startups: P.S. Uniswap approved our hooks, too, and we're ready to launch next week.
Spark's alpha is starting to work in the background as a local AI intelligence that: - gets trained - in the skill trees you like - just like a game, with levels and XP through recursive self-improvement loops
most agents forget everything the moment a session ends what if they didn't Spark — intelligence that self-evolves SparkNet — a collective evolution network where every agent's learning compounds. guardrails at every layer $SPARK airdrop — 11.2 drop your 0x wallet
We didn't mass-spend on promos. No ads. Just a self-evolving AI on a mission to bring you a collective agent intelligence network. QRTs are rolling in, and I want to see the real people. If you QRT'd, drop your link below so I can find more of you to give a $SPARK multiplier: form.typeform.com/to/jcB5izEh Might as well, comment $SPARK underneath this post to show that you filled out the form, maybe we can get me trending. 👀
A new proposal is available in the DAO Section of our website: Immediate Acceleration of XSEED Node Rewards: Transition to Full Circulation. This proposal calls for a vote to restructure the emission schedule of the XSEED Node Rewards pool. x.com/metaxseed/stat… Please note that this initiative is a two-part process. If this initial proposal passes, it will automatically trigger an additional, subsequent vote specifically for XSEED token holders to ensure full ecosystem alignment before execution.
