Well i generally look for signals that a place I might eat at knows how to cook. If I walk in and I see rats on the floor and theres no kitchen I probably won't be interested.
> Just because you can't separate the noise from signal with that easy check doesn't mean these people can't get the joy of side projects
I would love to meet these people that are getting joy out of seeing other peoples random fucking vibe coded apps that have zero rigor or skill applied to them lol.
Yes both of those are beyond worthless and largely uninteresting.
That being said, THOSE projects at this point have enough "activity" around them to make them at least somewhat worthy of a post. Which none of the vibe code posts have going for them.
How about Pi terminal agent, it's been my favorite terminal agent after trying CC, Droid, Opencode, Codex, Gemini, Amp. Just because you don't find valuable new side projects made using AI, doesn't mean they don't exist.
There's more projects I suspect are made predominantly using AI, but I don't want to speculate.
> You don’t have to announce your displeasure to the world.
If your spaces that were previously full of interesting things suddenly become deluged with uninteresting things then that is something to complain about.
You are not wrong. But you’re also not fully right.
I think you don’t see the full scale of the economic tail those tariffs had.
He raised tariffs illegally by 10% for most countries immediately, which triggered a bunch of negative economic effects around the globe in those countries directly tied to the illegal raise of those tariffs by who represents the United States of America.
Damages have to be paid to those countries and their companies.
Because those costs occurred from an illegal action. We do agree that if you do something the highest court has deemed illegal, if it caused damages to any party as direct result of that illegal action, the entity who suffered those damages should be entitled to claim damages, right?
A lot of companies had to deal with the same problems.
You can’t really plan exporting into a country that raises different amounts of tariffs basically over night depending on how his majesty, the king of the free world has slept the night before.
Someone needs to plan with the new realities, workers need to put in more hours, external expertise needs to be hired, all costs have to be evaluated, partners in the US might no longer be able to clear their inventory, new business terms need to be negotiated.
Don’t get me started about the Logistics troubles, but all of the above are costs which wouldn’t occur if the president had gotten legal advise from the Supreme Court about his economic plans before he did something illegal. Right?
So do you follow the law?
If yes, your conclusion needs to be that the president needs to write a lot of Cheques and probably needs the autopen. Because it weren’t only us importers and customers suffering from the presidents illegal action.
It's anyone who manufactures plastic or parts. 3D Printers are the wild west of printing your own replacement parts and soon the goal will to ban these things, unless there is right to repair.
Legislators are incentivized to push whatever sounds good to their voters and donors, their job is to do something, none of them have anything to gain from sitting on the sideline, even if they are powerless to effectively solve the issue. So they make something up. Both major parties push stupid shit that panders to their base whether or not it actually solves anything.
> Rebecca Beth Bauer-Kahan (née Bauer; born October 28, 1978) is an American attorney and politician who has served as a member of the California State Assembly from the 16th district since 2018. A member of the Democratic Party, her district extends from Lamorinda to the Tri-Valley region of the San Francisco Bay Area. She has been described as a women's rights advocate.
The real truth? Nonprofits like Everytown, funded fully by billionaires like Bloomberg, who are effectively bribing/coercing legislators with their money and power. They supply identical bills into many deep blue states. They’re all extremely invasive in this way.
Feckless democrats who want to appear tough on guns. Instead of taking on the NRA or lobbying groups they go after low hanging fruit to tout as victories to their base. It generates votes and wealth for the rep. Same thing with anti-trans bills from the right. Legislation that can pass through targeting small enough collectives that they don't have to worry about bad press.
All the news stories about ghost guns being 3D printed didn't hurt either. So they can sell a narrative of protecting people.
Seeing projects with first commits from 3-4 years ago feels like finding pre nuclear testing steel. No strong proof exists that this project was not conceived as slop.
Yep, i absolutely expect this to happen, the quality signals that humans use are going to be forever in flux now as the humans try to stay ahead of the bots.
For better or worse, a lot of people seem to disagree with this, and believe that humans reading code is only necessary at the margins, similarly to debugging compiler outputs. Personally I don't believe we're there yet (and may not get there for some time) but this is where comments like GP's come from: human legibility is a secondary or tertiary concern and it's fine to give it up if the code meets its requirements and can be maintained effectively by LLMs.
I rarely see LLMs generate code that is less readable than the rest of the codebase it's been created for. I've seen humans who are short on time or economic incentive produce some truly unreadable code.
Of more concern to me is that when it's unleashed on the ephemera of coding (Jira tickets, bug reports, update logs) it generates so much noise you need another AI to summarize it for you.
- Proliferation of utils/helpers when there are already ones defined in the codebase. Particularly a problem for larger codebases
- Tests with bad mocks and bail-outs due to missing things in the agent's runtime environment ("I see that X isn't available, let me just stub around that...")
- Overly defensive off-happy-path handling, returning null or the semantic "empty" response when the correct behavior is to throw an exception that will be properly handled somewhere up the call chain
- Locally optimal design choices with very little "thought" given to ownership or separation of concerns
All of these can pretty quickly turn into a maintainability problem if you aren't keeping a close eye on things. But broadly I agree that line-per-line frontier LLM code is generally better than what humans write and miles better than what a stressed-out human developer with a short deadline usually produces.
Oh god, the bad mocks are the worst. Try adding instructions not to make mocks and it creates "placeholders", ask it to not create mocks or placeholders and it creates "stubs". Drives me mad...
To add to this list:
- Duplicate functions when you've asked for a slight change of functionality (eg. write_to_database and write_to_database_with_cache), never actually updating all the calls to the old function so you have a split codebase.
- On a similar vein, the backup code path of "else: do a stupid static default" instead of erroring, which would be much more helpful for debugging.
- Strong desires to follow architecture choices it was trained on, regardless of instruction. It might have been trained on some presumably high quality, large and enterprise-y codebases, but I'm just trying to write a short little throwaway program which doesn't need the complexity. KISS seems anathema to coding agents.
I'm sort of happy to see all these things I run into listed out as issues people have so I know it's not just me experiencing and being bothered by these behaviors.
All of these bother me, but the null/default-value returns drive me insane. It makes the code more verbose and difficult to follow, and in many cases makes the code force its way through problems that should be making it stop. Please, LLM, please just throw an exception!
If AI is the key to compiling natural language into machine code like so many claim, then the AI should output machine code directly.
But of course it doesn't do that becaude we can't trust it the way we do a traditional compiler. Someone has to validate its output, meaning it most certainly IS meant for humans. Maybe that will change someday, but we're not there yet.
Ya i hate the idea that theres a difference, Code to me has always been as expressive about a person as normal prose. LLMs you lose a lot of vital information about the programmers personality. It leads to worse outcomes because it makes the failures less predictable.
Code _can_ be expressive but it also can not, it depends on its purpose.
Some code I cobbled together to pass a badly written assignment at school. Other code I curated to be beautiful for my own benefit or someone else’s.
I think the better analogy in writing would be… using an LLM to draft a reply to a hawkish car dealer you’re trying to not get screwed by is absolutely fine. Using it to write a birthday card for someone you care about is terrible.
I have zero interest in seeing something that Claude emitted that the author could never in a million years have written it themselves.
Its baffling to me these people think anyone cares about what their claude prompt output.
reply