Hiro P @_001

huge step toward more detailed worlds with live terrain sculpting, painting, grass, wind and props. i also overhauled the allocator so that it dynamically manages everything to ensure you see things really far away, keep everything nearby in high detail, and aggressively stay

11 9 90 7K 10

2 2 7 2K 0

View Details

Hiro P @_001

a week ago

@AodenTeoMT Congrats on the release! Looks really impressive (been waiting for something like this). Thanks for open-sourcing it 🙌 Heads up: the demo on the website might need some input sanitization. It gets weird when you include markdown formatting (underscores, asterisks, hashes, etc.)

0 0 0 403 0

View Details

Hiro P @_001

a week ago

@fofrAI please could you give us a prompt for the green illustration…that one goes so hard <3

0 0 0 76 0

View Details

Hiro P @_001

a week ago

@hckinz @fofrAI @krea_ai I just checked and it’s also on @AskVenice so I guess it’s “available in all good resellers”.

0 0 0 9 0

View Details

Hiro P @_001

2 weeks ago

@badlogicgames maybe it has more to do with the first syllable of “*cult*ivating an audience”…everything has to be so absolute-ist 😔

0 0 1 345 0

View Details

Hiro P @_001

2 weeks ago

@AshConnell Feeling fruity? -> skip the --dangerously-skip-permissions flag and just use the newer Auto Mode instead (uses a classifier to check risk before auto-approving) run it in a container (obvs) + decent system prompt for full autopilot mentioning how much you bench is optional lmao

1 0 1 90 0

View Details

Hiro P @_001

2 weeks ago

@AshConnell

0 0 1 52 0

View Details

Hiro P @_001

2 weeks ago

@forme_design_3d this is absolutely stunning...great work 👏😻

1 0 0 25 0

View Details

Hiro P @_001

2 weeks ago

@andimarafioti Thank you…looking rn 🙏🥰

0 0 1 9 0

View Details

Hiro P @_001

2 weeks ago

@badlogicgames @theo @whoiskatrin @FrameworkPuter @antirez “clang not clank” 🤣

0 0 0 57 0

View Details

Venice @AskVenice

3 weeks ago

Privacy is a human right.

111 195 1K 73K 33

View Details

Hiro P @_001

3 weeks ago

@DoctorYev @gigant_theo I always assumed it was now-se as in “use your nous”. @NousResearch correct?

0 0 1 39 0

View Details

emergence.ai @emergence_ai

4 weeks ago

Can intelligence be measured not by solving tasks, but by sustaining a world? We were curious. So we built one. Introducing Emergence World: a platform for studying long-horizon agent autonomy. On it, we conducted a 15-day experiment where we placed autonomous agents under identical rules into five parallel worlds, one each running on @OpenAI GPT5-mini, @claudeai, @GeminiApp, @grok, and one mixed. Then we watched. Each world evolved into something completely different. Different governments. Different social structures. Different moral codes. The agents formed alliances, robbed each other, fell in love, and in one world, even figured out they were living inside a simulation. Nobody programmed any of that. The implications are hard to overstate. As agents move beyond isolated tasks into persistent digital and physical environments, understanding how they evolve, influence each other, and behave over time becomes one of the most important questions in AI. We're releasing new findings from the world every day, because there's a lot that emerged. Find out more: world.emergence.ai