nesformer

AI

model weights emulation

SHOW HN2026

292points
150comments
#152of 4,366 in 2026
Top 4%of 2026 by points

How HN took it

MixedNo clear lean

8 positive, 18 neutral or asking, 2 mixed, 23 critical, out of 51 comments about the project. Thread score -0.18.

Idea: 7 for, 10 againstPerformance: 0 for, 8 againstExecution: 1 for, 1 againstDocs: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Impressive demonstration of how LLMs can compute

    From 2 comments
    • Woowww this is cool, not trained is even cooler--maybe I'm probably a bit naive, but to me it demonstrates an understanding of how an LLM can compute
      munro on HN
    • Omg what is this sorcery?!
      creposukre on HN
  • Clever builds on Qwenputer

    From 1 comment
    • > nesformer builds on Qwenputer by Divyansh Agrawal, which compiled a CHIP-8 and then a RISC-V CPU into Qwen3.5-4B. It reuses Qwenputer's compiler and its central trick: the…
      nico on HN

Objections

  • Runs far slower than the real console

    From 1 comment
    • >Overall, nesformer runs 150–290× slower than the real console. I like these kinds of projects because it helps to show the massive compute requirement between LLMs and ordinary…
      pbohun on HN
  • Unclear what the point is since logic circuits can be reduced to weights

    From 1 comment
    • I guess I don't understand the point of this. Of course a set of digital logic circuits can be reduced to a set of weights. Am I missing something?
      WoodenChair on HN

Requests

  • Explain the input and output in plain terms

    From 1 comment
    • Can someone give a TL;DR ? What's the input to the model? What's the output?
      mlmonkey on HN
  • Test with non-greedy sampling

    From 1 comment
    • It mentions a greedy decoder in the readme, I'm curious what would happen if you run it stochastically with T>0. Vibe NES? Or does it just crash.
      lachlan_gray on HN

Questions

  • How do they know it works across all inputs?

    From 1 comment
    • How do they know it's "working"? Did they test every possible input/output combination?
      amelius on HN

Alternatives named

  • Qwenputer, the CHIP-8 and RISC-V predecessor

    From 1 comment
    • > nesformer builds on Qwenputer by Divyansh Agrawal, which compiled a CHIP-8 and then a RISC-V CPU into Qwen3.5-4B. It reuses Qwenputer's compiler and its central trick: the…
      nico on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/50306442)