I remember cynically joking last year that all the "advanced" AIs like Claude were just the same kind of black-box LLMs but with a bunch of regexes glued onto them
-
@foone wait what happened lol, I know of the leak but that's all
-
I remember cynically joking last year that all the "advanced" AIs like Claude were just the same kind of black-box LLMs but with a bunch of regexes glued onto them
now that the source has leaked: HAHAHA
@foone honestly
from a description i got of claude's planning mode (that @iamada gave), i basically went "okay so its a bunch of prompts which shits out a few files in a specific way and then later on pastes them in the context window in a smart way so it can focus on one task at a time"
this is what ive been doing for myself for the last 6 years, its not anything special if an AI does it, and it can have an even worse track record at global recall than i do, lmao
-
@ShadowJonathan @foone yeah no I mean, are they just using someone else's llm
@VegaHarmonia @ShadowJonathan the model itself isn't included, I didn't mean it like that. maybe I should rephrase
-
@VegaHarmonia @foone there’s already decent analyses of the code, and indeed a lot of it comes down to careful system prompts
@VegaHarmonia @foone also word on the street is that claude is actually kinda shit in comparison, so makes even more sense
-
@VegaHarmonia I've seen some screenshots of the code, like the sentiment analysis part of the code is just a regex against a list of "angry" words
@foone @VegaHarmonia wait what, not even a proper text embedding model which runs through that???
also why would they be using sentiment analysis, for what, to tell angry devs to get a cup of water?
-
@foone @VegaHarmonia wait what, not even a proper text embedding model which runs through that???
also why would they be using sentiment analysis, for what, to tell angry devs to get a cup of water?
@foone @VegaHarmonia oh wait nvm it can be implicit negative feedback submissions when they detect the human being angry at the AI
hm
-
@VegaHarmonia I've seen some screenshots of the code, like the sentiment analysis part of the code is just a regex against a list of "angry" words
@foone that's...
Rofl
-
I remember cynically joking last year that all the "advanced" AIs like Claude were just the same kind of black-box LLMs but with a bunch of regexes glued onto them
now that the source has leaked: HAHAHA
@foone I mean was there any doubt?
-
I remember cynically joking last year that all the "advanced" AIs like Claude were just the same kind of black-box LLMs but with a bunch of regexes glued onto them
now that the source has leaked: HAHAHA
@foone wait, source? where? what?
-
@foone wait, source? where? what?
@freya they fucked up an NPM package and leaked all the source (well, the code, the models aren't there)
https://www.theregister.com/2026/03/31/anthropic_claude_code_source_code/
-
@freya they fucked up an NPM package and leaked all the source (well, the code, the models aren't there)
https://www.theregister.com/2026/03/31/anthropic_claude_code_source_code/
@foone oh that is fucking fascinating, I love it
-
@freya they fucked up an NPM package and leaked all the source (well, the code, the models aren't there)
https://www.theregister.com/2026/03/31/anthropic_claude_code_source_code/
@foone I want the models
-
@foone I want the models
@freya I'm always saying this too, I just don't mean the AI things
-
@freya I'm always saying this too, I just don't mean the AI things
@foone silly girl
-
@freya I'm always saying this too, I just don't mean the AI things
@foone I defintely mean the AI things, they're cute
-
@foone silly girl
@freya officially! I am pro-silliness! I am professionally silly!
-
@freya officially! I am pro-silliness! I am professionally silly!
@foone you are, it's one of the hottest things about you!
-
@foone honestly
from a description i got of claude's planning mode (that @iamada gave), i basically went "okay so its a bunch of prompts which shits out a few files in a specific way and then later on pastes them in the context window in a smart way so it can focus on one task at a time"
this is what ive been doing for myself for the last 6 years, its not anything special if an AI does it, and it can have an even worse track record at global recall than i do, lmao
@ShadowJonathan @foone app based markdown-based (executive) memory cache
but like, for a recursive predictive statistical model
-
J jwcph@helvede.net shared this topic
