https://www.bitsaboutmoney.com/archive/optimal-amount-of-fra...

They are optimizing towards making it easy to purchase things on a whim.

(TBH it's not clear to me that their marginal costs are low. They seem to pick based on narrative.)

I'm sure Nix is better, I just haven't needed it yet.

what does "economically" means here? would it cover teaching? child care? healthcare? etc.

https://en.wikipedia.org/wiki/Claude_(given_name)

If you are using mmap like malloc (as the article does) you don't necessarily know that you are "reading" from disk. You may have passed the disk-backed pointers to other code. The fact that malloc and mmap return the same type of values is what makes mmap in C so powerful AND so prone to issues.

If you sell a coding agent, it makes sense to capture all that stuff because you have (hopefully) test harnesses where you can statistically tease out what prompt changes caused bugs. Most projects wont have those and anyway you don't control the whole context if you are using one of the popular CLIs.

Even with the exact same prompt and model, you can get dramatically different results especially after a few iterations of the agent loop. Generally you can't even rely on those though: most tools don't let you pick the model snapshot and don't let you change the system prompt. You would have to make sure you have the exact same user config too. Once the model runs code, you aren't going to get the same outputs in most cases (there will be date times, logging timestamps, different host names and user names etc.)

I generally avoid even reading the LLM's own text (and I wish it produced less of it really) because it will often explain away bugs convincingly and I don't want my review to be biased. (This isn't LLM specific though -- humans also do this and I try to review code without talking to the author whenever possible.)

From reading your second link (and please tell me if I got it wrong) it sounds like it isn't actually tracking to training data but to prototypes which are then linked a posteriori to likely sections of the training data. The attribution isn't exact, right? It's more like "these are the likely texts that contributed to one of those prototypes that produced the final answer." Specifically the bit in PRISM titled "Nearest neighbour Search" sounds like you could have a prototype that takes from 1000 sources but 3 of them more than the others, so the model identify those 3, but the other ones might matter just as much in aggregate?

It says that the decomposition is linear. Can you remove a given prototype and infer again without it? That would be really cool.

This is why its not particularly problematic that it is closed source. Most people I've worked with who use it produce mathematical results with it that are fully checkable by hand.