xmcqdpt2

To start, this is more or less an advertising piece for their product. It's pretty clear that they want to sell you Allium. And that's fine! They are allowed! But even if that was written by a human, they were compensated for it. They didn't expend lots of effort and thinking, it's their job.

More importantly, it's an article about using Claude from a company about using Claude. I think on the balance it's very likely that they would use Claude to write their technical blog posts.

I'm sure some human writers would write:

> The specification forces this question on every path through the IMU mode-switching code. A reviewer examining BADEND would see correct, complete cleanup for every resource BADEND was designed to handle.

> The specification approaches from the other direction: starting from LGYRO and asking whether any paths fail to clear it.

> *Tests verify the code as written; a behavioural specification asks what the code is for.*

However this is a blog post about using Claude for XYZ, from an AI company whose tagline is

"AI-assisted engineering that unlocks your organization's potential"

Do you really think they spent the time required to actually write a good article by hand? My guess is that they are unlocking their own organizations potential by having Claude writes the posts.

Then pangram isn't very good, because that article is full of Claude-isms.

emacs + bitmap font for me and I'm continually shocked when I have to use something else by how it is blurry and laggy.

As is often repeated, the optimal amount of fraud is not zero

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

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

AI providers also claim to have small marginal costs. The costs of token is supposedly based on pricing in model training, so not that different from eg your server costs being low but the content production costs being high. And in many cases AI companies are direct competitors (artists, musicians etc.)

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

One time pads only offer perfect security once!

Zero trust security which is becoming increasingly common is based on removing the internal / external network dichotomy entirely. Everything should be assumed to be reachable from the open internet (so SSO, OIDC everywhere.)

I use debian + ansible and it requires discipline (you have to make sure you never do manual steps basically) but my entire ansible playbook makes server creation a 3 min process.

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

I'm recommending your for a mid-level management role at my employer right now.

This could have been html instead of whatever awful moving pattern it is.

SW50ZXJlc3RpbmchIFBsZWFzZSB0ZWxsIHVzIG1vcmUh

I wonder if it's related to the fact that Windows as such weird rules about allowed file names. Like not directly obviously, more like culturally inside microsoft.

is it most as an 50% of individual jobs? or able to produce 50% dollar for dollar?

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

By the definition above, it is possible to have AGI that is also much more expensive to run than human engineers.

I'd much much rather the model write the code blocks than the prose myself. In my experience LLM can produce pretty decent code, but the writing is horrible. If anything I would prefer an agentic tool where you don't even see the slop. I definitely would rather it not be committed.

I thought they picked it specifically because it is gender neutral, but now I double checked and apparently it's only gender neutral in French,

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

> Since the code in question was doing IO that you knew could fail handling the situation can be as simple as setting a flag from within the signal handler.

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.

Maybe all the users are OpenClaw instances?

There is no "why." It will give reasons but they are bullshit too. Even with the prompt you may not get it to produce the bug more than once.

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.

It's not reproducible though.

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.)

That would be great because "I got it from Wikipedia and Arxiv" isn't exactly useful.

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.

I think in practice it's less of a programming language and more of a scripting environment. It's like excel for math. There are many more people using it to produce mathematical results (like how excel is used to produce reports and graphs) than people who use it to produce programs.

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.

Le "tu" m'irrite vraiment venant d'un ordinateur.

Java also has covariant mutable arrays. I can't believe they created the whole language and didnt realize that covariant arrays are unsound? Or didn't care?

> Or go the opposite way: If you want a language that feels dynamic and leads to prototyping, well a type system that is total and complete might be too heavy. Instead of only allowing programs that are proven to be typed correctly you might want to allow all programs that you can not proved to be wrong. Lean into gradual typing. Everything goes at first and the typing becomes as strict as the programmer decides based on how much type information they add.

If you have generics and want type annotations to type check at compile time, you are going to need unification,

let l: List<Animal> = List(dog, cat)

At that point, you have written all the machinery to do inference anyway, so might as well use it.

I guess you could have a language where the above must be gradually typed like

let l: List<Animal> = List<Animal>(dog: Animal, cat: Animal)

but that doesn't seem particularly ergonomic.

and then verify that it obeyed the prompt!

Someone needs to build an agentic tool that does strict, enforced TDD.

> In the private market are there really so many companies delivering reports no one reads ? Why would management keep at it then ?

In finance, you have to produce truly astounding amounts of regulatory reports that won't be read... until there is a crash, or a lawsuit, or an investigation etc. And then they better have been right!

In Java you have instrumentation agents that can do arbitrary code rewrite at runtime, including for code that has already been JITted (causing a deoptimization of it). It's first-class supported, unlike in Go.

It's used extensively to (for example) add debugging or tracing to functions in libraries or to sanitize certain code path. At work, we were able to kill off jndi from Log4J to prevent Log4Shell within hours of the announcement this way while waiting for updates of thousands of dependencies.

Walk? Bike? Take the bus? People had kids for years before cars were invented.