prosunpraiser

I deleted my claude account the day the samples started preaching from the pope’s address and claiming 50% of the jobs will be gone while shamelessly stealing entire corpus of human data without attribution while preaching what you can and cannot do and maliciously degrading model quality.

I hope they either never make it to IPO or crash violently.

Lookout - next they will rewrite the color blue in Rust and claim advantages.

Desperate slithering snake fuck is what he is. First it wad 50% of jobs gone, then software engineering dead and now this spiel.

I have never yet had a set of words that I have grown to hate so much - “taste” and “moat” being at the top of them. It is almost always coming from people who have or know about neither.

(Agree with the article’s general sentiment - but just wanted to make this tangential comment)

How the hell is it even admissible?

Cause obviously what the gamers need right now is not games - but intrusive AI that adds no utility whatsoever.

Why didn’t I think of that?

There are alternative ways to gather telemetry data about your usage, then literally polluting the commit message / PR description of the author. Why even consider doing that in the first place?

Of course - finance is the best domain to depkiy a stochastic parrot which hallucinates and forgets stuff frequently and doesn’t follow your instructions - even with SOTA models. One where you need absolute accuracy and auditabikity.

Why didn’t I think of that.

Reuse is not always necessary - sometimes things are just done for fun and exploration, not for appeasing thirsty VCs and grabbing that market share.

Sheep mentality hard at work at companies. Just because Google does it (processes, technologies, systems etc), lets also adopt it without thinking whether its relevant in our context and use-cases. I bet the same devs from these firms who are asking to traverse a minimum spanning tree would fumble at even the slightest variation of the problem appearing in daily life.

A general rant.

Unfortunately the solution is quite simple - don’t release in EU.

You prove the point that these are just token generation machines whose output is psuedo-intelligent. It’s probably not there yet to be blindly trusted.

This. I use the same workflow. Also I am too lazy write and maintain notes - so I just use joplin for tags / metadata and typora (wysiwyg editor for md). Thinking and taking notes over typing on Typora is a godsend. Best $15 I have spent.

Writing todos as checkable list items in markdown and hitting them off one by one and tracking notes on the same md under different headings works like a charm. No more JIRA / excel / context switch.

I haven’t seen on how it fares on uncensored use-cases, but from what I see Q5_K variants of Mistral 7B are not very far from Mixtral 8x7B (the latter requires 64GB of RAM which I don’t have).

Tried open-webui yesterday with Ollama for spinning up some of these. It’s pretty good.

Not sure if this helps but this is from tinkering with Mistral 7B on both my M1 Pro (10 Core, 16 GB RAM) and WSL 2 w/ CUDA (Acer Predator 17, i7-7700HK, GTX 1070 Mobile, 16GB DRAM, 8GB VRAM). - Got 15 - 18 Tokens / sec on WSL 2 with slightly higher on M1. Can think of that to about 10 - 15 words per second. Both were using GPU. Haven’t tried CPU on M1 but on WSL 2 it was low single digits - super slow for anything productive. - Used Mistral 7B via llamafile cross-platform APE executable. - For local-uses I found increasing the context size increased the RAM a lot - but it’s fast enough. I am considering adding another 16x1 or 8x2.

Tinkering with building a RAG with some of my documents using the vector stores and chaining multiple calls now.