

You mean LLM, not agent?
Or are you using agent to mean “instance of specific LLM model hosted on X”? Your description is also a bit weird offline + firewall (firewall against what? Local hosting environment?)


You mean LLM, not agent?
Or are you using agent to mean “instance of specific LLM model hosted on X”? Your description is also a bit weird offline + firewall (firewall against what? Local hosting environment?)
Don’t. They had 180 million usd income, with operating cost of 3 million usd, and they currently have over quarter BILLION is net assets. They (Wiki foundation) are at the point where they become cancerous to the Wikipedia - e. g. they are currently union busting.


It’s 90% right 90% of the time. But the most important part is the last 10%.
No LLM model system card claims such high rate as 90%. Fable claims in its system card, what, 40% hallucination rate?


I am also curious what AnBee tried to edit and was refused.


LLMs generally work in one way. They get the prompt and give an answer. CLAUDE.md, system promp, rules, memory, tool defintions, mcps are different ways to prefix your prompt with extra information or context.
Skills, or plugins, are a way to inject less information until is needed (you can think about them as prefixing your prompt with “if you are asked about pizzas, add to context separate file pizza.md”).
What you could add to CLAUDE.md depends on what you’re doing. Generally it should be context LLM cannot infer relevant to all/most task performed in given project.


People are arguing with you that tokens are “real” - they miss the point. You cannot predict how much “tokens” you will spend for a given prompt.
That’s the problem you’re highlighting, we are charged for a metric we cannot estimate before buying to make an informed decision how many we want to spend vs the quality of the outcome.
The charge and quality is arbitrary, and we can’t trace if we actually spent as much as we were charged for.
Anyone who waffles about tokens being real should - I believe missed your point.


If you run “agentic coding harness” or any kind of goal oriented loop then tokens goe brrrr.
And LLM sellers are pushing for that (duh), as they managed to convince people to use infinite monkeys typewriting until they make Hamled.
(Type made on purpose)
Yup, totally agree, the whole “cat mama” shit is weird to me. Like mental.
I love cats etc, but people are really weirdly thinking about them. I honestly think some should get tested for toxoplasmosis.


Why is it “a wild standard”? We’re taking workers rights. China is a big, wealthy developed country, why would we not expect from it at least good labour laws? The worker exploitation is not admirable. And I detest anyone who says otherwise.


??? Are we having two different discussions?




You forgot, you have to ignore all the good things China does
For it’s workers? China is still behind EU when it comes to workers rights and benefits though? Good for them they are slowly, very slowly progressing in that regard.
E.g. paid time off in China is 5 days a year, +5 for every decade of cumulative work experience; it starts at 4-6 weeks in the EU; China has more of it’s own youth muddled in gig economy then EU (don’t get me started on how exploitative gig work is, it is disgusting any country allows for that practice).


It was, but the actual problem I have with the app is that it had 90% margin. Talk about quick and dirty cash grab.


He personally guarantees 40 billion from 111 bilion for the Paramount - Warner Bros acquisition.
I do wonder if this might put the financing there at risk lol.


Boy you’re in for a ride.
Palantir runs on Oracle Cloud.
Oracle finances Paramount buying out Warner Bros.
Other shady shit Oracle does: https://thedreydossier.substack.com/p/the-merger-that-needed-a-war
Basically think Oracle is a competent League of Evil that can hide from the media spotlight.


If ADHD is common enough to be prelevant in 5% of population… Then to me it seems like its not something we should be drugging people for, but instead adjust the lives to it?
I mean we don’t give “righ-handeness” drugs to left-handed people. We give them left-handed scissors.


I vastly prefer suntan background and blackish font. White on black makes my eyes tired.


Literally! They were told to return to office to achieve higher productivity (it was circling the news around September?)
You should read their 2026 report - 3x more bugs, 10x code churn, 10% LESS deployments, 50% more epics (my take is smaller epics lol)