I have successfully reverse engineered and decompiled Snood for the GBA (2001), a game originally created by @GCDaveDobson over 25 years ago, entirely driven by AI. Every byte matches (SHA-256). I used Opus, Codex, and dozens of parallel DeepSeek V4.1 agents to attack different parts of the codebase. The first step was finding the compiler, where I sent off some agents, and they discovered it was agbcc, the GCC 2.95 compiler from Nintendo's GBA SDK, and verified it by recompiling standard library functions like memcpy and getting byte identical output to the ROM. For the first week or so, matching was stuck at 3% as I had no idea what I was doing. Then one afternoon, I experimented with agent swarms and went from 7% to 81% in about 5 hours. I ran over 20 DeepSeek agents in parallel in multiple waves, each AI assigned its own function in its own sandbox, so they never stepped on each other's work. The bigger AIs merged each result only after re-verifying their work, picking and choosing what was best. The last 19% took several more days, and the last 300 bytes were very difficult compiler forensics. This work is particularly suited for agentic workflows as the reward is easily verifiable (matching rom percentages). Why Snood? I have a faint memory of playing this game at around 3 years old. I also remember hearing the video game soundtrack and wondering "How did they fit that in the cartridge?" Well now I have my answer, they used the GBA's four built-in sound channels in a sort of midi-like way to generate songs on the fly. Only the sound effects are real samples, 8-bit audio at about 11 kHz. I also wanted to choose a game that was relatively obscure, had little info, as Pokemon has been analyzed to death (and I didn't grow up playing Pokemon!) I don't have an accurate number on the cost, but it was around 4-5 billion tokens. I do feel a bit strange, as now I was no longer tell AI what to do, I was telling AI what to tell AI what to do! The knowledge I gained from this project is mostly high level about how to coordinate agents, rather than technical details (though, now that I have the code, I can ask any question and figure it out). What would've taken a team of hobbyists years took me about two weeks of on and off work. I think we're about to see a lot of forgotten technology and code get preserved, which, in the face of AI writing more and more code every day, is kinda amazing in my eyes. The future is very bright for technological preservation efforts. If you're interested in the code, let me know below. Enjoy the cutesy explanation video!

😅 this is what happens, when frontier decision models.... are starting at free

We are jev-ifying open source models @FeatherlessAI - which surpasses jev in evals - and includes image/vision With a starting price of [check notes]... Free? simple-jev-demo-api.featherl…

Jev, now with open weights + vision. Classified 1,697 SF Tech Week events with Gemma 4 26B-A4B. Zero labels. No fine-tuning. Jev-ify any open-source model on SimpleJev.

It seems everyone has found fun use cases for #Jev. Well, how about Jev for protein binder classification? ➡Give the blog a read: blog.colbyford.com/zero-shot… #zeroshotclassification #proteinbinders #proteindesign #bindingassay @adaptyvbio @TwistBioscience

Jev, now with open weights + vision. Classified 1,697 SF Tech Week events with Gemma 4 26B-A4B. Zero labels. No fine-tuning. Jev-ify any open-source model on SimpleJev.

Now we just wait for Chinese dev teams to copy Jev and open-source it. It looks super lightweight, so it should run easily on consumer GPUs.

love jev, but upset it - isn't open source? - it lack vision capability? We fixed all of that, introducing SimpleJev.ai A fully open source library which takes any HF model and Jev-ify it, with an API endpoint Now on github, and live in production at @FeatherlessAI

I build an undetectable realtime adblocker extension with typesafe It checks every dom element and classifies as ad/non-ad and removes it if true Extremely fun to work with, expecting an incredible shift in how AI is being used in the future

🚨Claude is telling users to go to sleep mid-session, and nobody, including Anthropic, seems to fully understand why it keeps doing it.

The model appeared defeated, spending the next several hours doing essentially nothing but farming potatoes. Stream viewers noticed and complained that Astra needed to "pick up the pace." Astra also seemed to become paranoid about creepers: "GREEN tall thing ahead was SUGARCANE, NOT creeper!" At times it was hard on itself: "you can screw up and drop things"; "do NOT waste another night chasing dark pink pixels" (its own disparaging wording for pigs); "our last tool stupidly ended Slabsselected/rightUP and 15sec thinking killed us".