Yeah, seems like this could be achieved by using https://github.com/streamich/memfs/blob/master/docs/snapshot...

Weird they don't use it - might backfire hard

BTW does anyone know of good assistant voice stack that's Open Source? I used https://github.com/ricky0123/vad for voice activation -> works good, then just using Web Speech API as that's the fastest and then commercial TTS for speed as couldn't find good one.

I tried Kokoro-JS that I think runs in browser and it was too way too slow with latency also not supporting language I wanted

I have a 5070 in my rig. What I'm running is Kokoro in a Python/FastAPI backend - I also use local quantized models (I swap between ministral-3 and Qwen3) as "the brains" (offload to GPT-5.2 inc. web search for "complex" tasks or those requiring the web). In the backend I use Kokoro and generate wav bytes that I send to the frontend. The frontend is just a simple HTML page with a textbox and a button, invoking a `fetch()`. I type, and it responds back in audio. The round-trip time is <1 second for me, unless it needs to call OpenAI API for "complex" tasks. I am yet to integrate STT as well and then the cycle is complete. That's the stack, and not slow at all, but it depends on your HW.

> Potential accidental data leakage from the “future”

Exactly. Makes no sense with models like grok. DeepSeek also likely has this leak as was trained later.

AFAIK the whole morphology is decided in distributed computation fashion via electrical potential changes, at least according to experiments by Michael Levin

Yeah compared to animals we have a lot of extra bootstrapping outside of physics/chemistry alone via culture and stored information similar to how cell DNA bootsraps via physics, human mind boostraps via stored information in human "network" (talking, internet, books) after being born.

I can see a perl comeback

Just add godot example games nearby and it will learn functions / usecase from them. Just say in instructions BTW you have example games in "examples" directory to check

You can also use "repomix" tool to bundle whole source of godot into single file and tell it to search it when uncertain

Why use an extra tool, when you can tell the LLM where the Godot source is to be found in case it wants to investigate some details? What is the benefit of using repomix?

I think it's due to improvements in vision basically, the arc agi 2 is very visual

Vision is very far from solved IMO, simple modifications to inputs results in high differences still, lines aren't recognized etc..

It's also easy to spot as when you are tired you might misrecognize objects, I caught myself with this when doing long roadtrips

AFAIK this is actually a separate mechanism, which is part of the visual cortex and not the retina. Essentially recognizing even a single object requires the complete attention of pretty much your entire brain in the moment of recognition.

What I am referring to is a much more basic form of shape recognition that goes on at the level of the neural networks in the retina.