Viewing profile — search_facility

This "hidden knowledge" is fun to read but pain to remember and use, especially when working with multi-platform environments // Switched from bash to plain python scripts for shel…

... Today its "Claude just needs to write it" and the "hard part" is the prompt :)

Current situation exist presisely due researches of 20th century though. This is largely connected things

There are still problems though - in Chrome translation addon simply no way to login properly so its broken //

Also represents good test coverage

It's the opposite, engineers do know. Claiming otherwise is way too generous and over confident. I mean between this two "knowings" the Claude inner workings are much more clear fo…

Well, at the very least we have a base to distinct different kinds then. Probably the main problem of people implying LLM consciousness is that they imply LLM have human-kind of co…

It is useful, so yes

MOE basically work that way already, QWEN/etc with low active params (A-number in name) allows to inference big models locally (only active params have to fit into memory)

With both cases the agent doing something is human . And human beings are indeed conscious. Outside human needs LLM are useless. Math, as a tool, is just a proxy for people using L…

> weak reasoning once you get off the beaten path Yep. And LLM engeneers improving this issues see perfect correlation with only one thing - data quality and quantity through train…

Math used in LLMs is perfectly reducible and Gödel have nothing to do with it - inside commonly used axioms (which sufficient for LLM to exist and outside of Kurt Gödel scope) ther…

+100, companies certainly have direct interest in pumping asset evaluation, and emotional attachment is financial valuable thing. Emotional attachment sells better than xxx this da…

Imho no, math itself have no conciousness. Quite confidently its a helpful tool that does not act by himself.

I can not simulate my brain, it's a huge stretch to imply this. But with LLMs - anyone can simulate LLM. LLM can be simulated without any uncertainties in pen and paper and a lot o…

Since the times GPT-2 was reimplemented inside Minecraft - its quite obvious LLMs are just math. Nothing else, by nature. Modern LLMs have the same math as in GPT-2 - just bigger a…

With current standartization the issue of "page not working on non-Chrome browser" is non-existent. Thanks god nowadays everything (pages) work everywhere in very similar manner, I…

But on the other hand, adding LLM with strong guards (not yet here but doable for popular attack vectors) into the human loop can drastically eliminate insider factor, imho.

probably 8M params are too much even :)

Well, this is a business model, not a coincidence... They are in the battle of selling fresh hardware each and every year consistenly

Exactly!

Interesting! Can it be used in Google Colab to open temporary access to python server? NGROK can be attached this way in 6 lines of code

biology plays the role, certainly, but nature was trying to capture a model for 3D physical interactions first of all, physics first. And final choice of two 2D sensors is explicit…

Our 3D visualization relies havily on photons doing the heavy lifting of traversing 3D space in straight lines, people get, you know, accustomed to it. In fact how we see things is…

Interesting research, but it is still fascinates me why AI devs of current SOTAs ignore possibility to add numbers as first-grade citizens to AI. like for example suggested here: h…