AirMax98

I am actually going to guess that this is in fact unfortunately not an LLM. I have been made a few audio webpages and don’t think a lot of these mistakes would have been made, even though the model can’t hear :^)

I normally don't comment on matters of taste like this, but wow this is brutal. It's like someone threw the site in a vat of molasses.

Similarly blessed that I am too stupid to comprehend this post. This person compares themselves to Prometheus and is begging for cash? What? Why is this not flagged?

It's a bit like a payday loan — the drivers need money _today_ and effectively borrow against the depreciation of their vehicle.

I hear you — but what do you think Spotify or any of the other streaming services are? In my mind, algorithmic streaming services have much more in common with this "experiment" than your local radio DJ.

At this point I think many of us are similarly exhausted by this sort of trite exercise. I really don't need some VC backed startup to show me this sort of output any more, especially when the output in question is obviously boring and substandard.

Probably one of the most reckless things I've seen in software. Beyond safety or quality, at the very least: what about all the existing contributors' PRs? Fuck 'em?

Right — it does seem cool but the voice is patching over a major gap. If I'm talking already, why wouldn't I just describe what I'm looking at and have the AI grab it for me?

I do agree. The Gary Tan takedown page is equally sensational, kinda for no reason? There’s a lot to rag on with Gary, but this webpage makes it seemed like he killed a guy or something.

It’s also kinda the case for sports too — I literally just watched LeBron throw an alley oop to his kid a few nights ago.

I actually don't understand how this would affect bankruptcies — why?

OpenAI is the founding sponsor of the new, open-source Warp repository.

Big bucks from OpenAI is my guess. I could guess the strategy is to try to take a shotgun approach at Claude Code.

What are we even doing here.

I have no idea what this has to do with aerospace, but I know a bit about software and this does not look great. Cursor is obviously on a serious decline and has little to no moat in the area they are building in (IDE), which we kinda now know is maybe not even the right area (CLI). I feel like this is just a bad move?

https://archive.is/gbdJ8

Dumb devices have gotta be a billion dollar market at this point.

I’m very amazed by this site linked in the Wikipedia: https://libraryofjuggling.com/Tricks/3balltricks/Cascade.htm...

Supposedly from 2014, but looks a fair bit older.

Come on man.

This feels like slop to me.

It may or may not be, but if you want people to actually use this product I’d suggest improving your documentation and replies here to not look like raw Claude output.

I also doubt the premise that about malformed JSON. I have never encountered anything like what you are describing with structured outputs.

Fun fact: under the hood atproto bears many similarities to blockchain... it was funded in during the 2019/2020 crypto craze. I'm not too involved, but outside of a consensus mechanism, atproto looks a bit like a chain, kinda like IPFS.

This was my immediate thought as well. A great time to ask yourself — why am I literally paying for any of this? At best I literally don't use any of these services, at worst they are actively used against me.

Glad you pointed this out… kinda hilarious someone looks at these musicians, their output, and their fans and thinks that “being from the west coast” is the primary factor here.

So true — this thing is designed to go on our streets; I expect an attitude of maximum compliance. This shit can literally kill you if something goes wrong?

I worked at a payroll backed loan company and can say there is not many people in the space, for many good reasons.

These banks do not exist.

And make sure you steal from the right people.

I really disagree with this too, especially given the article's next line:

...You’ll be forever tweaking individual lines of code, asking for a .reduce instead of a .map.filter, bikeshedding function names, and so on. At the same time, you’ll miss the opportunity to guide the AI away from architectural dead ends.

I think a good review will often do both, and understand that code happens at the line level and also the structural level. It implies a philosophy of coding that I have seen be incredibly destructive firsthand — committing a bunch of shit that no one on a team understands and no one knows how to reuse.

The remaining developers seem to implement things primarily client side, to the extent I even wonder if they have lost their ability to safely roll out backend changes.

Thanks for putting this into words — I have also noticed this and felt that product decisions have been shaped by this force of institutional rot.

Seriously agree — try using something like Sonnet 3.7 and then switching to Gemini 2.5 Pro. The code that both output is fine enough — especially given that I mostly use LLMs as a fancy autocomplete. Generally a better prompt is going to get me closer to what I want than a more robust model. The speed hit with Gemini 2.5 Pro is just too substantial for me to use it as a daily driver.

I imagine the speed difference might not matter so much if you are performing seismic updates across a codebase though.

Death spiral is unfortunately a very correct term for this. I really can't express how different the conditions of public transit in SF and Philly are. Riding the L in Philly is unbelievably sketchy at night (passes through K&A) and I would not ride it alone if I were a woman. This is one of the main intra-city commuter rail lines in Philly. At this point, there are so few viable options that I can't really recommend public transit in Philly to anyone. Compare that to SF, where I literally take public transit everywhere, every day.

My first guess is that this is an unauthenticated server action.[0]

0 - https://blog.arcjet.com/next-js-server-action-security/

100dvh is your friend.