News for hackers. Stuff that matters.
Re:Show HN: Factorio Learning Environment – Agents Build Fac... by vessenes on Tuesday March 11, 2025 @11:41AM (#43333584)
Trivial as in only engineering work, sure. But it’s a lottt of tokens. Long context models do a number of things to get all that working context in; some of those things elide details / compress / have token segments that are harder to reason about. When a burner inserter at a location takes up like 50-100 tokens, and you want it to reason about 100 of them, this is still a pretty challenging task for any LLM.
Re:Show HN: Factorio Learning Environment – Agents Build Fac... by jillyboel on Tuesday March 11, 2025 @11:44AM (#43333621)
Ah, I don't know much about multi modal models but I wonder what they'd think of pixel art representing the factory where each pixel is a point on the grid and each color is a specific entity, perhaps ignoring things such as bots flying about. Probably easier to comprehend than an actual screenshot?
Re:Show HN: Factorio Learning Environment – Agents Build Fac... by kridsdale1 on Tuesday March 11, 2025 @11:56AM (#43333738)
I mean at some point you compress the board state down to Dwarf Fortress with an extended ASCII representation for each grid-state (maybe 2 bytes each?)
Re:Show HN: Factorio Learning Environment – Agents Build Fac... by vessenes on Tuesday March 11, 2025 @12:38PM (#43334261)
Lots of questions here - you need item, orientation, info about pipes (2 directions) , belts (3 or 4 colors x2 directions). Do you wish Circuits?
Re:Show HN: Factorio Learning Environment – Agents Build Fac... by noddybear on Tuesday March 11, 2025 @12:31PM (#43334166)
The thing is that when you create a dense ASCII representation, any gain you might make from the spatial relationships is lost by: a) the tokeniser not working on characters alone (remember strawberrry), and b) the increased number of 'dead' tokens encoding not very much.

Our sparse encoding seems to confuse the models less - even though it certainly isn't perfect.