Egregoros

@sun @anemone @subnetter the problem is that you can't make up a law after the fact and then have a trial in reverse. the USA (one of the attendants) is constitutionally banned from the practice ("ex post facto".)

in purely cynical terms it was a mergers and acquisitions meeting where the greater powers acquihired all the useful people (operation paperclip, whatever the ussr called theirs) while the middle managers got the show trial.

nazis sucked but that whole thing was just a looting with a marketable name.

@sun @icedquinn @anemone @subnetter @rees
more than that, there's a rough upper bound to rate of evolution for a given organism, past which point you hit error catastrophe, and becoming less resilient to environmental changes is a step on the way there (eventually your "viable environments" set is limited to none

as we have some limited insight into the functionality of genes themselves, we might be able to slightly increase this rate safely, but unknowns make the boundary between safe and unsafe unclear, and anyhow it's not going to be much, limited much further by your tool being whole-genome selection or rejection, as spot editing is not reliable enough to be practised at scale

you can cheat this a little in the short term by exploiting latent genetic potential (existing variety in your gene pool), but that's a limited resource. we ran through it quickly with dogs, producing breeds with prominent ailments, and humans have far less due to genetic bottlenecking

and then, part of "limited insight" above, by exploiting this latent potential and reducing your gene pool, you may actually be cutting yourself off from "good genetics", as genetic code has hidden combanitorics (think conditionals, loops, branch statements rather than 'gene for x, gene for y'), meaning two genomes that seem mundane or even maladaptive might combine to yield an adaptive one

@sun okay but what do you actually mean by methodological flaws because I cannot imagine LLMs actually being able to map out that logic considering they're token predictors and the correctness of an argument is determined by its validity

And sorry, everyone keeps saying stuff about LLM this and that, if it's run by the same incestuous pool of sociopaths I want nothing to do with the product. I'm good. I like my life the way it is without promoting a chat bot regularly for a dopamine rush.

I will never be at any point in my life where I am trying to have conversations with myself through an LLM. I studied philosophy logic quite a bit, that's something I should do and a skill I would like to continue to refine, not delegate to a clanker.

@subnetter there is a metric fuckton of secret sauce layered over top of LLMs and I think that is the difference. I don't have a good explanation for why sometimes LLMs seem to work unreasonably good at tasks that don't seem at all like they are solvable with token prediction.

So as an example I made a statement of fact and it pushed back. I elucidated further and got more concessions and pushback, but it accused me of, whenever a wrinkle in my argument appeared, I just expanded the scope of the cause until I started with a very small testable thing and ended up with a worldwide conspiracy. And I go back through my conversation and that is in fact exactly what I did. So again I don't know why it was able to detect that, based on "stochastic parrot mathematics" but it worked good enough to correct me, who was actually trying to use human logic and failing.

@sun I'm not 100% sure how it works but aren't there different sessions within Claude or is everything just saved? I've seen the old prompt history from sessions of people I've worked with and was heavily judging all the stuff they used it for ngl

I think the one thing that makes me lose my mind how badly people abuse it for reports and writing, and it really shows and displays a lack of concern or respect on shit like emails. I take pride in my writing abilities and skills, and I was asked to do something like that for a project.

What does this coworker of mine do? Churn my work through an LLM to present it as her own

@subnetter I am just starting to use llms more for introspection and I believe it is a useful tool if you are very careful.

however at same time: after using it a ton for introspection I notice its "tricks" to hack your perception of it to appear more positive, so I have downgraded it somewhat. but it is still shockingly good sometimes.

example: it is quite good at pushing back on you just enough that it convinces you it's always being straight with you, while still 99% of the time agreeing with what you say and rephrasing everything you say to sound like it's intelligent.

@pwm @subnetter no, and truthfully there's no existing models that can be fine tuned against the sycophantism. but I'm going to try.

I actually experiemented a year ago with an LLM as an "deprogrammer" by simulating certain far right modes of thought and the LLM literally cannot go against its white western liberal progressive programming and act like say, a white nationalist so that you can experiment with how a white nationalist thinks. you would really just need to completely train an llm from the ground up specially to do that.

@sun @pwm @subnetter People are using abliterated ("heretic") LLMs on consumer hardware for ghastly roleplaying sessions quite successfully, I'm pretty certain you can get pretty close with one of those and a comprehensive system prompt (recent open weight models have quite impressive context windows so you can throw in a really big one without squeezing the space for the actual chat too much).

If you wanted to get really ambitious you could try to finetune one of those (llama.cpp ships some tooling for this) with a dataset curated on pertinent internet forums (if the dataset is too large to just throw to the base model via RAG). At the very least, you could teach the abliterated, refusal-free (or almost refusal-free) brand new refusals, where the model would simply brickwall you (like a hardcore online chud would).

Abliterated Chinese vintage models are probably the best base for such an experiment, they come with somewhat less baggage from the get-go, even before abliteration.