Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • It is weird and almost alien how AI designs factories. When Claude announced Fable 5 they also did a Factorio demo that was the same kind of designs and a lot of hand feeding and direct insertion. In some sense it proves to me that llms are not just copying and are actually creating a bespoke solution. But I honestly expected more from frontier models
    by kanemcgrath
  • Factorio is a much easier game without the bugs being a pain in the arse as you expand - i wonder how Sol would handle the bugs
    by VoidWhisperer
  • It doesn't seem to understand the core mechanic of Factorio, which is putting outputs onto belts and routing them to other inputs. It does this in a few places, but for the most part everything is put into chests and moved around by the player.
    by fasterik
  • One limitation of these type of demos (and similar with Minecraft, etc) is that: 1. Putting into "peaceful" mode makes response time a non-factor 2. These models have read and have access to every guide and video ever published on the subject. Most humans, especially on first play, learn game systems and interactions from scratch, then develop novel strategies and plans and "hypothesis test" their way into beating the game.

    This is still impressive compared to where we were a few years ago, and being able to synthesize all existing information about a game and then play it to completion in a semi-realistic setting is great.

    At a quick glance someone might mistake this for "brilliant AI solves Factorio", when in reality, given a similar but different game where it wasn't gifted all the information or training data (e.g. massive videos and screenshots) it might fare terribly (as others have pointed out in comments).

    by program_whiz
  • Watching AI play games is fun, but I can't wait for someone to crack having small LLMs in games to enrich them in useful and interesting ways.
    by mickeyp
  • If you haven't been keeping an eye on LLMs playing games, GPT 6.1 Sol can new beat games 100% vision-only (without harnesses that give the agent extra information about the game). Pokemon is no longer a difficult challenge for it, even with additional difficulty restrictions such as hard mode and level caps. Recently, GPT 6.1 Sol beat Final Fantasy VII and its bonus bosses vision-only surprisingly quickly.

    I suspect Opus 5.5 can do even better but there aren't as many people testing it.

    by minimaxir
  • AI playing video games is a funny twist of faith. We call the AI-controlled characters NPCs, but now we've become NPCs watching AI play itself. How weird is that? At the same time this might help AI learn better - each game is a new system, a new set of rules to make sense of, each one has a unique tutorial aimed at human intellect to keep engagement, as well as teach you how to play.

    As much as games are similar, especially within the same genre, the nuances are important.

    I'd personally be impressed the moment the AI manage to play the games following those newances and being efficient as well as effective.

    by lenikirilov
  • > The rocket launch was only achieved through significant ‘manual’ effort on Sol’s part as it papered over its late-game failures to connect certain production systems by repeatedly ferrying supplies between areas of the factory.

    Robots: they're just like us!

    by mwt

Explore Birbla archives