We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for three js render of it. Opus went off for ~2 hours and wrote 5500 lines of code that (procedurally) rendered the story. It's kind of janky but fun. But it's a bit mindboggling that the LLM has to place and orchestrate various polygon assets in (x,y,z) coordinates and write code that animates it all, and that it even does anything at all.
I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free". There might be a lot more. But I'm excited about creating hyper custom worlds that you can imagine dropping players into, e.g. here to participate in the LoTR story as a spectator NPC, or one of the characters, or etc. Something like an ephemeral GTA of X on demand.
Last thought is that the domain of worlds/games exposes a weakness in LLMs: they can't easily audit their work because they aren't able to efficiently and natively perceive videos or play games within them. Here, Opus 5 had to very slowly and painstakingly take screenshots at different points, and it messed up a few times and created a bunch of jank. An example of raw capability (multimodal, gameplay) that I think is still quite lacking.
@_bnovc@draginol He was using Blender headless CLI, then I told him to use the MCP Server. The Blender MCP is better for him to iterate. But I didnt spent a lot of time on this
@_bnovc@draginol I tell him to build some low polly animals and this is the result, I could iterate more but I decided to make it on https://t.co/lR9vz6rFsJ
@_bnovc@draginol Opus 5 is pretty good doing 3d. But you need to build something where he can preview what he is building, like taking screenshots etc, then he will iterating it. Itโs not one shot like people say
my wife asked me to clone a site for her for work and in the process of doing so claude appears to have logged into their unsecured admin portal to screenshot the layout
@1994Will@wesleycancampos @arthurzinhoocrf irmรฃo, ngm liga pro corinthians, maior rivalidade hj em SP รฉ com o palmeiras.
corre atrรกs que no jogo mais importante do confronto deu Flamengo.
Regenerating code only works if the system is fully defined by specs and tests โ most real systems arenโt.
They embed time-based and irreversible business decisions, historical state, and distributed behavior.
AI output is not deterministic.
Regeneration isnโt a replay โ itโs a new interpretation, and therefore a new decision.