dbreunig

This is a case where we basically did test it on everything! Because the emulation community maintains conformance tests with over 3k of golden instructions. (And this is why Opus was able to so effectively build it; it found the tests)

This has the nice side benefit of letting the 1gb of weights compress down to ~3mb (since it’s mostly empty)

A couple thoughts on the process here…

First off, Opus 5.5 built working weights and code with only two prompts:

1. Read this article and any relevant source code: https://divagr.com/blog/qwenputer. Then explore if you could emulate the chip and ram in a Nintendo Entertainment System (as people do today with FPGAs in MISTRs) using this technique. If so, what size model would you have to build and if you could use smaller faster ones, could you get it to be at the standard clockspeed.

It returned charts well illustrating any model would be _slow_. But it's still fun, so the second prompt was:

2. I think we should build it! Just for fun. It's okay if it's not fast. We want to be able to have the weights, and a cli to run them that we can point at a ROM.

Now while this was an _epic_ run by Opus (5.5 is a crazy capable model), this is a surprisingly well-structured challenge.

There is a long-lived and incredible community of classic gaming emulation work online for it to reference. And that community has created…conformance tests! Opus found them and built against one, that has >3k golden instructions: https://github.com/christopherpow/nes-test-roms/blob/master/...

Also, there is the original Qwenputer repo that Opus used to drive the weight writing. That was essential.

But this is a great example of what these models can do with proper reference materials, great specs, conformance tests, and clear direction.

Doesn't work for all cartridges (I didn't run Opus that long, but it could keep going). Works with Super Mario.

But to answer your question, it's in the readme: https://github.com/dbreunig/nesformer#how-it-was-checked

The whispers around this pattern have started to increase. I would love for someone to run a proper experiment.

Have been waiting for this to manifest for years: https://www.dbreunig.com/2023/05/17/prompt-injection-seeding...

I'm the weirdo who is clinging onto GLM 5.2. 5.3 seems to have picked up the bad writing from Opus 5.

I think it’s a fine response when you say, “Doesn't feel well informed enough to give advice,” because I said 5.2

Ok, buddy.

I can’t host GLM 5.3 yet, so my agents still run on 5.2. But the fact that 5.2 is sufficient and there’s another gen in the wings kinda proves my point, imo.

Wrote about this awhile ago, and it hasn’t changed:

> Time and time again, when talking to people who rely on ChatGPT, Claude, Perplexity, and other general AI tools, I hear them say, “AI is incredible. It handles nearly everything I throw at them.”

> “What does it fumble with?” I’ll ask.

> “Well, it still gets things wrong when it comes to my line of work.”

https://www.dbreunig.com/2025/04/08/on-ai-observational-comi...

> What you get is a beautiful animation that is 100% accurate and free of hallucinations

How does he know?

I got an early tip on this and used it to build a brand mood board and it crushed previous attempts with Claude. Highly recommend.

Elizabeth Lopatto at The Verge makes a strong case we _do_ have proof that Musk is actively gathering and throwing fuel on the fire: https://www.theverge.com/ai-artificial-intelligence/929129/s...

> But the thing is, Molo doesn’t actually have to be good at this job, because the point of this trial isn’t to win — though I’m sure Musk wouldn’t mind a win. The point is to punish Altman, Brockman, and OpenAI. Musk has done that pretty thoroughly — reinforcing in the public’s mind that Altman is a liar and a snake. This morning, I read an exclusive in The Wall Street Journal that assorted Republican AGs and the House Oversight committee wanted to look into Sam Altman’s investments. References to the trial are peppered throughout the article.