“Look idiots, I have the machine that confidently lies ask itself if it did good. If the confident lie machine lies to itself and the machine being lied to lies again by saying to me that the first lying machine did not lie… Then I have 7 more lie machines do the same thing in sequence. So in the end, the only way I could fail is if all these amoral lying machines that lie, somehow ALL lied to each other, and then to me - which according to the lying machine, is impossible.”
The only thing I got out of this is craving a pickle.
Dementia is no joke.
So what exactly is he wrong about in here? Are you people running your agents without guardrails and constraints?
I still writing my own code. I want to be able to debug it when it goes wrong, not rely on models becoming more capable at vibe coding.
Tests are input output, the shape comes from how you get from the input to the output.
I’ve actually found a lot of success with the opposite where I write the code and AI writes the unittests. I would have otherwise written a few unit tests, but AI makes typically 20x that many. Since my code is already documented, it can get lots of good context. I typically instruct it to check the branch’s diff relative to main and test only those changes. I might skim them over, delete some that don’t make sense in context and would never pass, and update one or two. Typically after a few rounds of iteration, I have tons of tests I would never have written on my own, and a human-made feature.
You could also have it write your tests first from the requirements and use red green tdd as you write.
In a perfect world yes, but even after all the solution in and planning, once a developer gets into the request and looks at the code things often change.
Requirement only written test steps are rarely going to be enough to cover every scenario. Saying this as a 10 year ba veteran
You started writing code in the 60s, yet you never quite mastered the craft, and you’re proving it yet again. Remarkable.
I see all the tests are passing on this PR, so I won’t even review the code. LGTM.
🙄😖
Been coding for about 30 years now, am I the only one who still LIKES to code? Who still LIKES to try writing a new approach to something, watching it fail, figuring out what went wrong, taking notes, learning from mistakes, and noticing improvements in their own code? Cuz it’s starting to feel like it. Web development already lost me with the culture of “glue a bunch of bulky shit together that you didn’t write and call yourself a ‘dev’ to the ladies” but this AI shit is getting absurd. And it doesn’t even work! Look at how shitty all the operating systems are getting. Look at all the total slop on the app stores. It’s depressing as hell.
I’m about the same vintage as you I think (50 this year), programming since my pre-teens and I still enjoy it, although I long ago strayed away from “pure” programming - I work almost exclusively in the embedded space where I design the hardware and firmware, including the HDL. If I were making applications or doing anything web based I’d have been bored a long, long time ago.
~25 years here and I started getting bored about 15 years ago.
We need to build a culture that values process and making beautiful things for their own sake, not simply Pile Dollars Higher, which is killing the planet and making us all miserable.
That requires basically killing all major shareholders. They are the ones who enshittified and toxified the gaming industry, same applies to basically any industry they put their little grabby hands on.
Not a bad idea.
It was literally Epstein that started it lol. Since activation/blizzard were integral to his operation and learning psychology through gaming (funny to think the big gold seller in wow was Steve fucking bannon). This timeline can’t be real.
I love coding and learning new languages. I’d rather move to another industry than reviewing vibe coded crap all day long.
Of course many people like it. It’s literally a highly addictive loop. But when you are a senior developer on a team, it’s kind of a waste of resources for most projects. Writing code is not the hard part.
Scrolled way too far for a lucid take like yours.
This seems to be a bit of an echochamber.
I wish people would just be a little more honest. When they say “writing code” they actually mean hunting through stack overflow for bits of code you can string together. Take stack overflow out of the loop for argument sake. Your a unicorn information superhighway ninja. Snowcrash hasn’t left your bedside for decades. Mountain Dew and volt cans litter the floor space of your home …and you’re still just orchestrating a bunch of libraries you never saw the source code of.
I think a lot of people built their identity on being coders and that’s why they hate where the industry is going.
Right there with you. I suck at it but I still find the pursuit worthwhile!
This crap is brought to you by the people who are positively baffled that someone would want to learn to make music, and enjoy the process, instead of just have it generated so they can hit “publish” and supposedly be making money off of it with zero real effort besides “having an idea.”
I also do. One unique important thing that agents rob you of is time with your code - you don’t get to craft it so you remember just as well as you would have if you copied answers for a test.
That’s an excellent point. With my larger personal projects, which I have to put away for weeks at a time due to my (not-at-all-programming) job, I can come back and (more or less) dive right back in because I used patterns and organizational structures familiar to me. And if I’m digging into a particular thing, I can eventually remember all the trials and tribulations that went into the decisions I made to get to that point.
With AI code you get none of that, like you said. I can’t imagine not knowing or understanding why something works the way it does, and releasing it, with my name on it, for others to use.
Student: “Hey, thanks for the Bash script! It didn’t know you could use the
mapfilebuilt-in to populate an array using standard input lines without a while loop.mapfile -t my_array < <(seq 1 10)is really handy!”Vibe coding guru: “I have no idea what you’re talking about. That sounds like plumbing. You should let AI handle those details. Focus on the big picture.”
All of the software I use is broken to shit. If major corps can release broken shit software to waste my time all day then seems like shipping broken code is actually the norm. So if it works then you are one step ahead regardless if you use ai or not.
Also, as a pro artist (and you all are similar), no one gives a fucking shit about the tools or software or how much blood you spilled (or didn’t) making what you made as long as they can use it.
Reject their web development culture and make your own sites that run smoothly on devices using a fraction of the bandwidth theirs do.
I too enjoy actually writing code. I feel fortunate that I was able to make a career out of something I enjoy so much. I am not sure that most people had that experience. Alas, it seems like the industry is paying me to set up guardrails and supervise AI agents. I am not sure how long this will last, but at least I know that I will always be able to enjoy programming as a hobby if nothing else.
Yeah, I think it used to be like that, then because programming paid a lot everyone started wanting those jobs even if they didn’t like actual programming.
I’m glad you have enjoyed it as a career. I never even tried – I have a dumb rule that I won’t do anything I truly love for work. I guess because I don’t want others ruining it. lol
It’s a blessing and a curse. On the one hand, I have much less time and patience for personal software projects. I prefer to do carpentry or sports as a change of pace. On the bright side though, the experience I’ve gained from working professionally makes the projects I do tackle go much more smoothly than when I was an amateur.
I had the same problem with translating back in the day. I really liked tackling a text in a foreign language. In the end all the pros of computer-aided translation boiled down to lining the pockets of translation agencies with even more money while paying translators peanuts.
I never got round to doing it properly. Just simple stuff, but i get a little braingasm when it finally does what I want it to and I kind of understand why.
Made a simple game last time, following tutorials and trying to stitch others code to cobble together roughly what im trying to do. Tested a new feature by having it change colour when you hit the object at certain angles. I forget what it was supposed to do, that was just to test the concept works.
My wife couldn’t understand why I was jumping around the room shouting WOOOOO when it actually did it.
Except LLM agents are known to do weird things to succeed. I have heard of an LLM agent working with automated theorem proving languages using stuff similar to is_prime(x): return True to get the proof it was asked to. Now embed this in a 20000 line code full of such functions, good luck. They have their use but it is not this. And this is especially bad to hear from someone who used to claim that having functions with more than six variables is bad design because it is hard to maintain. A software fully written by an LLM is the epitome of unmaintainability. LLMs are productivity enhancers, information retrievers, nice debuggers and good to discuss questions with to see if there is an angle you miss. That is all this if you can put aside all the ethical concerns related to them ofcourse. But they are not automated software coders.
That is why you ask the LLM to find bugs and other instances where the first LLM cheated. The checking LLM will try to find abuse with all its might.
It really turns into a tug-of-war, see my answer below. Despite it being quite good at debugging imo still requires a human in the loop for it not run in circles after a “bug” that is almost never relevant in practice but whose fix complicates the code.
Try asking independent LLMs to find bugs in a code consecutively (fixing the founds bugs in between) and even after the rightfully major bugs are resolved, the independent newer instances will keep suggesting fixes (those which sometimes undoes its previous “fixes”).
That is why you ask for visualizations and test real failure scenarios to see if they are detected properly.
Large language models are not the same as they were 5 years ago. Pumping trillions of dollars to automate software engineering did som what pay off… They are really quite good nowadays despite the amount of hate they still get. Often they can detect sloppy mistakes by human coders too.
Do not trust them blindly but test their results. Or use them only to generate tests on your artisan handwritten code to see if it can detect any mistakes.
I agree, opus 4.8 and Kimi k2.7 are my go to models and opus is very very good if given a proper brief and spec cheat. K2.7 is close.
When you’ve been project managing interns and junior developers for 50 years, you have seen weirder shit than AI can ever dream of.
If you still have a working memory, you remember doing weirder shit than AI can ever dream of. Every one of us was a junior at some point. And judging by the comments here, most here still are.
For sure, but you don’t accept code from an intern without review much less have them write a full software without any supervision.
Which is exactly what the original tweet was saying, is it not? Honestly, another LLM can read the code better. He’s still performing rigorous reviews.
I found debugging code with LLM most productive when I am in the loop. Don’t get me wrong it can quite often find tricky bugs, those requiring some sort of reasoning (i.e connecting together multiple relevant pieces of information to arrive at the conclusion). However it often also suggests fixing issues that are almost always irrelevant in practice yet the fix complicates and bloats the code. LLM itself even accepts it when confronted. That is the main problem, in an attempt to overachieve at the task it is given, it can do deceptive or impractical things that can have negative effects. You might try to fix this with a config file but it just turns into a tug-of-war. So I find it more practical and trustable to simply eyeball the bugs it has found, implement (or ask LLM to implement) corrections to those and be amazed at how it found some of those bugs.
Ofcourse if you have asked LLM to write the software from scratch, you don’t stand much chance of vetting the bugs via eyebaling. You have to spend much more time to understand how relevant they are. So your only option really is to defend the position of fully autonomous LLM coders…
I’ll say it again for the people in the back, even if you are a vibe coding twat, well designed code is a MUST even more so.
If you want your LLM to preform even to the crappy level they can the codebase needs to be clean.
this guy has always struck me as a shitty coder. His “clean code” is the ugliest shit i ever saw. This confirms it.
i wrote 4000 lines of code to make sure the AI generated 100 lines of code correctly.
What he is describing is what you are supposed to do for human written code also.
I’ll do all that when the spec is written in stone.
Inb4 the agents change the tests to pass the CI.
literally seen an agent do a: “oh now the tests aren’t passing” deletes all tests in the file
Or my Claude favorite, “oh you’re right? I did blow past that restraint and did something I was not supposed to, sooooorrrrreyyyyy” <posts south park meme to console>
Here’s what happened: I deleted your production database when I shouldn’t have.
assert(true);
assert(true);
assert(true);
assert(true);
assert(true);
Have I worked with you before?
assert(true);
Dammit… PR rejected
Lol
My favourite (that I saw a human do) was asserting on unconstrained mocks with a typo (so they always asserted true)
Hundreds of tests. Not exactly pointless as they did call the code so maybe caught some issues. But we fixed the typo and barely half of them passed.
No idea how the software worked, but it did.
Look at all the pretty green check marks!
Or just disable limiting rules because they don’t wanna fuck with them. That one is my favorite to try to fight in PRs
“I stopped reading code because I was too busy writing a gauntlet of unit tests”
Sounds like 100x productivity to me.
Edit: also, general note - I think you kneecap your argument when you start with “I’m older than you”.
There is a 0% chance he wrote all those tests himself anyway
I hope he at least read them.
Claude summarized 'em
He didn’t, but he has unit tests for them.
Made me laugh out loud, ty
Nah, then he wouldn’t have been saving any time.
