Elektrine lite

← Feed

@tatterdemalion@programming.dev

Post #1302721

2026-03-27 12:29 UTC

LLMs might suck at this game but I'm pretty sure Deepmind's deep reinforcement learning AI could solve these easily. EDIT: I know you guys hate AI around here, but you need to at least be aware of what the technology is capable of. From 11 years ago: https://youtu.be/V1eYniJ0Rnk

Replies (4)

  • @33550336@lemmy.world 2026-03-27 12:55

    if only it would exist

    Open ##1302821

  • @yogurt@lemmy.world 2026-03-27 19:48

    No because it's designed with all the things AI can't do. Breakout is a quick repetitive loop of pass/fail linear progression. AI melts down when it has to backtrack and keep track of multiple pieces of context and figure out how to do something but not do it yet.

    Open ##1302824

  • @bss03@infosec.pub 2026-03-27 18:59

    The founder of ARC worked at Google until 2024 and wrote 2.5+ books in Deep Learning. So, I expect some of these benchmarks are based on limitations seen in Deepmind. That said, it would be interesting to see how well Deepmind does at these tasks. My understanding is that the private tasks would still be dynamic enough to require "on the job training" so an Alpha-Go / Alpha-Zero / Alpha-Fold approach is unlikely to do well on ARC-AGI-3. Still, I think commentary around models (including, but not limited to something from Deepmind) attempting these tasks would be much more interesting than most of the discourse around generative AI, whether text, image, video, or code generation.

    Open ##1302825

  • @kshade@lemmy.world 2026-03-28 14:11

    I guess the idea is that yes, machine learning algorithms could be used to solve these, but that's essentially brute forcing. You can make a simple algorithm learn how to complete Super Mario Bros or how to make a virtual robot walk, it just takes millions of iterations. The promised actual artificial intelligence wouldn't need that.

    Open ##1302830