acedTrex

Quite a fascinating level of incompetence from openai here. Not unexpected obviously but come on, if you are getting outsmarted by an LLM you deserve it.

Ive typed out several things, none of them really capture succinctly the level of disdain I have for people that this article is describing.

I cannot fathom the idea that one is warping their work on a given engineering problem around the availability of a magic next token predictor box.

Its pretty snappy/responsive for me at least so thats good. Normally LLM slop sites are pretty at first but sluggish as hell. So some level of skill went into this one.

I mean, I am no LLM lover but in the possible "success case" there are also many many other cool/good to humanity use cases.

Whereas ads are almost exclusively negative.

The fact this is controversial is wild and a grim sign for an already struggling industry.

I left because Github became too LLM obsessed and I find that to not align with my personal ideals. Its not really deeper than that. The programming community will continue to splinter more into those that care about the craft and those that only care about outcomes.

It comes down to culture on the team, if you think your leadership will allow that/you won't get a bad perf review for doing it go for it. That is sadly not a lot of peoples reality.

For the person who rejects PR suggestions, it makes me less inclined to participate in those PRs. Why spend the time doing a thorough review if it's going to get rejected anyways.

This is why you leave blocking suggestions and force the conversation if you think it is important enough.

Yep, without a decent team culture this is what LLMs force, the slop deluge is just overwhelming without leadership asserting "no, stop"

Ultimately you just let bugs through because the alternative is spend an inordinate amount of time communicating with someones claude through PR comments about what the shape should be.

Career was fun while it lasted. I suppose its a blessing a to get to do a job that you enjoyed for as many years as I did.

You get better at proactively setting up feedback loops and the ability to respond quicker.

Saying "im sorry this is broken it will take us a few weeks to fix it" feels infinitely worse than "im sorry this is broken give us a few hours and we'll get it fixed"

This is exactly what i do, its very easy. I mirror across codeberg, github and a local forge instance

I started using zig more heavily for some edge device ML inference projects lately after watching Andrews jetbrains interview and it really really resonating with me on a personal level.

Am also really overall enjoying the language, it def has some rough spots regarding documentation and the stdlib but overall has been very nice to work with in neovim.

I can't throw 400k but I'll go ahead and pledge some dollars towards it as well.

Just to be clear, i also find the "determinism" points to be a bit misleading if the intent is accurate, obviously there has been some level of non determinism in compilers and computing forever. I think the better word is "predictability."

When you write code and it compiles the outcome that you get is entirely predictable. An LLM prompt is not at all predictable.

Overall though agree entirely with your sentiments. And my llm usage is also blacksmith esque, in that its like hammering steel into shape. "Sharing my prompts" would be hundreds of "move this method" "rename this to that" "extract line 12-24 to a new method" etc etc

I despise this retort that i see constantly, in no way shape or form is it remotely an accurate analogy. They are two completely different things and its dishonest to attribute the two together.

Theres really no diff between a rubber stamp and an llm review, they both do the same thing.

Coding is largely solved!!

Gatekeeping is good, we need more of it in the llm age lest we be overridden with slop.

The hard part now is liking the industry around it

This has always been the hardest part, its just the past few years its gotten exponentially more difficult.

The trick to getting good at using LLMs for software is to learn how to make _all_ projects low-stakes.

this doesn't really work in the real world. There are many things that actually matter, engineering is fundamentally about handling them.

I am becoming a better architect with AI, because I am spending more mental energy in that lane, getting less embroiled in the nitty-gritty of the code.

I don't believe this, every architect ive ever worked with that was not regularly in the weeds on various things in the codebase were universally terrible and out of touch.

I'm not following what "I dont understand" would entail here. The choice is fairly binary.

I will pick the software not existing at all every time. Easily without a thought.

More people building things is straightforwardly good

No it's not, its the opposite actually its very bad and leads to far far more noise in the system to sort through to find value as someone who's competent.

Ya it's definitely been an ongoing process. LLMs have just accelerated it.

Do you ever actually think during this process? or could I train a monkey to do this same activity with the same outcomes?

Here we go again

I read this as im "reviewing" a 100% claude generated ten page incident RCA report. It's mostly wrong but bringing that up is not useful so just rubber stamp and move on.

we as a culture will gradually find a resting place here in regards to "proof of work" but it will be a painful decade in the meantime.

"Created the nuke" is the best framing. Detonated a WMD on the field of rigorous practice.

The floor has been raised significantly as to what bad code can even look like

It's hard for me to disagree with this take more wow. LLM slop code is TERRIBLE and verbose.