has anyone managed to use any of the AI models to build a complete 3D fps game using web GL or open GL?
Gemini 3
291–300 of 1001 posts
Re: Gemini 3
#292Earlier quoted context omitted.
Ironically, OpenAI was conceived as a way to balance Google's dominance in AI.
I thought it was a workaround to Google's complete disinterest in productizing the AI research it was doing and publishing, rather than a way to balance their dominance in a market which didn't meaningfully exist.
Elon Musk specifically gave OAI $150M early on because of the risk of Google being the only Corp that has AGI or super-intelligence. These emails were part of the record in the lawsuit.
Re: Gemini 3
#293Out of curiosity, I gave it the latest project euler problem published on 11/16/2025, very likely out of the training data
Gemini thought for 5m10s before giving me a python snippet that produced the correct answer. The leaderboard says that the 3 fastest human to solve this problem took 14min, 20min and 1h14min respectively
Even thought I expect this sort of problem to very much be in the distribution of what the model has been RL-tuned to do, it's wild that frontier model can now solve in minutes what would take me days
Re: Gemini 3
#294Earlier quoted context omitted.
I'm asking about Gemini, not Copilot.
Copilot lets you access all sorts of models, including Gemini 3. https://i.xevion.dev/ShareX/2025/11/Code_9LWnDqpeCe.png
> Copilot lets you access all sorts of models
It's not exactly the same since e.g. Copilot adds prompts, reduces context, etc.
Re: Gemini 3
#295Re: Gemini 3
#296I think I am in this AI fatigue phase. I am past all hype with models, tools and agents and back to problem and solution approach, sometimes code gen with AI , sometimes think and ask for a piece of code. But not offloading to AI and buying all the bs, waiting it to do magic with my codebase.
I agree but if Gemini 3 is as good as people on HN said about the preview, then this is the wrong announcement to sleep on.
Only reasonable thing is to not listening to anyone who seem to be hyping anything, LLMs or otherwise. Wait until the thing gets released, run your private benchmarks against it, get a concrete number, compare against existing runs you've done before.
I don't see any other way of doing this. The people who keep reading and following comments either here on HN, from LocalLlama or otherwise will continue to be misinformed by all the FUD and guerilla marketing that is happening across all of these places.
Re: Gemini 3
#297From an initial testing of my personal benchmark it works better than Gemini 2.5 pro.
My use case is using Gemini to help me test a card game I'm developing. The model simulates the board state and when the player has to do something it asks me what card to play, discard... etc. The game is similar to something like Magic the Gathering or Slay the Spire with card play inspired by Marvel Champions (you discard cards from your hand to pay the cost of a card and play it)
The test is just feeding the model the game rules document (markdown) with a prompt asking it to simulate the game delegating the player decisions to me, nothing special here.
It seems like it forgets rules less than Gemini 2.5 Pro using thinking budget to max. It's not perfect but it helps a lot to test little changes to the game, rewind to a previous turn changing a card on the fly, etc...
Re: Gemini 3
#298I was hoping Bash would go away or get replaced at some point. It's starting to look like it's going to be another 20 years of Bash but with AI doodads.
Re: Gemini 3
#299Re: Gemini 3
#300Impressive. Although the Deep Think benchmark results are suspicious given they're comparing apples (tools on) with oranges (tools off) in their chart to visually show an improvement.