all 13 comments

sorted by: hot top controversial new old
[–] 8 points 13 hours ago* (3 children)

I was not expecting AI to be a catalyst to reinvigorate the game modding landscape, but AI tech seems to be filled with unintended consequences. Hopefully these types of processes can be achieved with local hardware running open models in the near future. Micro-scale community compute could completely facilitate a departure from the tech behemoths' walled gardens.

  • source
  • hideshow 3 child comments
  • [–] [S] 6 points 12 hours ago (2 children)

    Qwen 3.8 is actually fairly capable already. You do need a beefy machine to run it, but it's very much in consumer grade at this point. My expectation is that within a few years we'll be able to buy something like this, hopefully at a cost of a raspberryPi to run it https://wccftech.com/alibabas-tsmc-built-5nm-risc-v-chip-xuantie-c950-now-runs-qwen-3-8-27b-model-natively-unlocking-massive-vertical-integration-tailwinds/

  • source
  • parent
  • hideshow 2 child comments
  • [–] 4 points 12 hours ago (1 child)

    This is really damn cool chip design. The liberation of technology for the proletariat by China really just keeps rolling along. When the AI crash hits the financial markets, China will be ready with commodity solutions.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 1 point 12 hours ago

    problem is people half ass these things for clout and who knows if the games are even completable

  • source
  • [–] 1 point 12 hours ago* (4 children)

    I'm still skeptical that the LLMs are really doing "clean room decompilation." It's plausible that all of the source code for these games is included in the training data. Most of the examples in the article are owned by big publishers who may have made secret source code access deals with the AI companies. In the case of The Binding of Isaac's flash version, the LLM might be trained on the pre-existing decompiled ActionScript.

  • source
  • hideshow 4 child comments
  • [–] [S] 6 points 12 hours ago (2 children)

    Nah, LLMs can absolutely do decompilation using tools like Ghidra. I used LLMs to reverse engineer the proprietary codec for my Nikon camera RAW format, and it worked great.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 12 hours ago (1 child)

    I mean, Nikon is another big software company. I don't see why their code wouldn't end up in the training data either.

  • source
  • parent
  • hideshow 1 child comment
  • [–] [S] 3 points 12 hours ago

    Sure, maybe proprietary code from every company is in the training data magically. But it's obvious that the LLM wasn't just regurgitating code that it memorized because it solved the problem iteratively over many days. And LLMs don't work by memorizing things like a database in the first place.

  • source
  • parent
  • [–] -3 points 13 hours ago (2 children)

    Nothing with "AI" is awesome.

  • source
  • hideshow 2 child comments