Dev is screwed.

I've had it on my todo for years to work through ddc and trusting trust.
Which is a method to verify a compiler is matching its source and thus trustworthy.

An orthogonal approach is reproducible builds, which among many benefits can make sure a few people verifying things benefit everyone who can then see they have the same verified binaries.

If I remember correctly, they used KenC to bootstrap the Go compiler.

Quis custodiet ipsos custodes?

Amazing story, i loved it.

lol wow this is gold

The ending is rather unsatisfactory.

except for poison to take in, it should be a pretty significant part of the dataset. Also, ngl, i'm not much informed on the topic, but aren't all the datasets, if we're talking about generic diffusion models and LLMs, already been formed? From what i gather, the innovation in AI mainly comes from utilizing new architectures, rather than training a model on something unique.

Should be relatively easy, with the amount of once trusted packages that become attack vectors

Ugh. Fuck "AI" and fuck Anthropic. But please read how the "watermarks" work. TL;TR its like a seeded run in a video game. With the seed and pseudo rng, you get the outcome i.e. the extruded text. In the watermark its the reverse, outcome + prng = seed. The result will be the same "quality" extruded garbage as before.

The CPU runs Minix, are you going to tell me you don't trust Minix now?

Real developers know LLMs are basically just a tool for finding examples and helping with syntax.

Your words on gods ears. I also found it to be reasonably useful when you're stuck in the documentation of a library clearly written by and for people who already know it.

Unfortunately people who do not understand code are blissfully ignorant at what garbage they have the machine spit out. Of course until the LLM nukes their whole project folder or even disk because the probability engine unfortunately picked "clean slate" as the most probable next thing. Not as if that ever happened at companies, lol.

Yeah, I'm in a similar camp. AI is very good at dummy data and unit tests, fairly good at log traces and making fiddly changes across an entire codebase, somewhat good at boilerplate and making derivative code based on something similar, and somewhere between "passable" and "awful" at everything else. I use it for what it's good at with heavy manual review, and just about the only time I run with the first thing it spits out without looking it over is if it's something that is never intended to leave my machine.

I can also usually sift the usable from the not-usable in the automatic PRs that our company has turned on. In the past couple of months, the ratio of good comments to bad ones has gotten slightly better; from about 20% good to about 55% good.

But I'd never let an AI write a team message or acceptance criteria or anything. That's a human job.

I think it's supposed to be that how AI turns high level instructions into code is compared to how compilers turn code into assembly. Implying that using AI is just a natural extension of the handing off work to the computers that we've already been doing.

I wonder if you gave different AI models some c++ or something and told them to write assembly based on it how well they would do compared to an actual compiler

Linus Torvalds

Not exactly, but something along those lines.

We are talking about a guy still using mailing lists and patch files to conduct development on one of the largest codebases in the world, not exactly someone who jumps on any new shiny thing just to sound smart.

https://thenewstack.io/torvalds-ai-programming-productivity/

That saying (or, dare I say, thought-terminating cliché) glosses over the consideration of risks and costs that result from its uncritical usage. No sane person should trust it without serious reservations just because it fits the purpose, and that's true whether or not it bears the latest combination of letters peddled by tech bros. It's a dangerous, irresponsible mentality. It's a tool the same way a sledgehammer made out of plutonium is a tool.

If a tool costs more to be made than the equivalent of buying every single person on earth a loaf of bread every single day for 300 days, only for it to have niche uses, that only helps what is possible with already existing tools, is it worth it?

And then your boss says: "Use it for everything or you're fired. Why are you using less tokens than anyone else? You must be more productive or else..."

People probably say that about asbestos too.

Na, fuck that shit. Just don't use it.

Will share the down votes with you, because I think the same.

Claude opus is better than a significant amount of people I've worked with, and it's still significantly cheaper when now. Mind, we are not professional developers, but we need to develop a lot a DS solutions.

In this case it could just be a contraction for "developers".

But far more likely to just be wrongy used.