troupo

Last time I tried it (quite some time ago) it didn't have anything built-in for file uploads: https://github.com/bartblast/hologram/issues/228

I've tried to keep an eye on its development, but I don't think file uploads were mentioned yet (and there's nothing about them in the docs).

The only thing that's stopping me from trying this currently is file uploads.

Otherwise it's a really cool project

When did it become normal to talk about open source like this?

Why does something being open source absolve it of any sins?

TVs are good when used appropriately. We watched Macbeth for the literature class.

I doubt US tech understands.

For one, they are deeply in bed with the current administration (for any definition of current, past, and future).

For another, they fight tooth and nail any and all sovereignity of data even within their own walled gardens. See decade of battles by Google, Apple, Facebook etc. in the EU.

Many many words, no meaning.

Because you keep vibe-reading what I write.

Here's what I literally started with: "I always have to correct its hallucinations during the day. Why would I ever let it run unsupervised overnight?"

Which means what? Oh. It says literally what it says.

Here's how I continued: "Which tests and optimizations do you propose to run after a night of supervised work when one of main things that all agents keep doing is 'load all records from db , and filter them in memory'?"

What does this mean? Oh, it means the literal meaning of the sentence. It also probably strongly implies that I actually look at the code produced by these things, as otherwise I wouldn't know things like "oh, the agent loads the whole db into memory and filters it into memory, we have to correct that".

You literally completely ignored all that and got irritated by just this sentence: "It's now become so bad, I had to literally vibecode a separate linter for this".

Because, see, I had to write a tool with the use of AI and run it against existing code, and correct it until it worked to my satisfaction so that I don't have to spend a lot of my time correcting a repeating error, so I automated the finding and the correction of a repearting error using a linter. And instead of writing that entire sentence I used the word "vibe-coded".

So no you've wasted a lot of breath arguing... what exactly is it that you arguing? Your inability to read what other people write? Functional illiteracy?

Edit. Since you're so keen on chasing me in other comments it's unsuprising that you again completely ignored the one comment https://news.ycombinator.com/item?id=48965638 where I link this: https://news.ycombinator.com/item?id=48962703 But sure. How dare I use the word "vibe-coding" incorrectly when it was coined by the Lord Our God Karpathy Himself.

Yes. "People don't use alternatives not because they literally aren't allowed to, but because other things matter more"

John Oliver did a report on militarization of police 11 years ago. It's only become worse since: https://youtu.be/KUdHIatS36A?is=C86HI8463VZnqjXU

Because there's no legal way to use Claude Code on subscription otherwise

A TUI outputting nothing but text shouldn't consume 70 GB RAM and yet there they were just half a year ago: https://x.com/jarredsumner/status/2026497606575398987

They couldn't even fix flickering in their TUI and their new renderer is complete garbage.

They succeeded despite their tech.

You started with "scanning logs for errors" with LLMs which is one of the most stupid things could do with LLMs on a "serious SASS product with hundreds of thousands of users" (aka logs easily in gigabytes to hundreds of gigabytes per minute).

But now it's suddenly not "we use LLMs to scan logs for errors", but "we use actual tools to find erots in logs, but then just hand them off to an LLM and hope for the best".

As in "let's repeat what @troupo said but pretend it somehow goes against what @troupo said" lol

The lack of long context is the main reason that I still end up using Anthropic.

Anthropic's "long context" is mostly marketing bullshit. It semi-reliably holds about the same amount of info, and then starts suffering the same issues.

Is the high expense coming from cache misses?

Yup. They can't keep your workload in cache forever, or they would run out of cache for users.

I wonder would starting new sessions and having to re-read the contexts and results anyway be any cheaper.

Yes, that's what they recommend

and then just wait for the next prompt

A single session running for multiple hours is prohibitively expensive, as per Anthropic. Regardless of whether it just waits for a prompt or does something.

I regularly have my code reviewed by professional devs

I also read my code regularly

So you're literally doing what I am talking about.

Demagoguery. Your "great product" (where is it? show me these great products) will have wildly ineficient code and things like "read the entire DB into memory" regardless of the prompt.

plenty of people have figured out how to get this to work

Plenty of people claim they have figured it out. In reality these people are full of shit and assume that if LLMs can produce working software, it's great working software. And also assume that LoC is a measure of quality.

Because without fail all the models keep doing this: https://news.ycombinator.com/item?id=48962703

And you can only see that in your "great product" if you actually read the code and understand what's going on.

You see, there's your problem right there. You're vibe coding, which by definition literally means you're unwilling to look at the generated code. That's not what successful ai assisted software developers are doing. YOU HAVE TO READ THE CODE.

I guess you vibe-read what I wrote. Let me write it again for you: "I always have to correct its hallucinations during the day. Why would I ever let it run unsupervised overnight?"

Imagine for example looking for http status code 500 in an api log over the past hour.

1. On a blog that no one visits maybe?

2. It's called a grep

3. For bigger projects it's called sentry

Running tests that the agent created for its own hallucinations? Optimize using another hallucinating agent?

Which tests and optimizations do you propose to run after a night of supervised work when one of main things that all agents keep doing is "load all records from db , and filter them in memory"? It's now become so bad, I had to literally vibecode a separate linter for this. And that's just one of the problems.

On all projects I've run any of the models they:

- infinitely duplicate any and all code, helpers and components

- infinitely duplicate CSS (because they duplicate components)

- continuously write code like "read the entire db into memory and run a filter function on retrieved data"

- continuously write code like "call db with multiple queries for each element in a list"

- etc. etc.

Why the hell would I ever want to run them unsupervised?

scanning logs for errors

famously a good job for a tool that takes 10-50k logs to run out of context and forget what it's doing.

I always have to correct its hallucinations during the day. Why would I ever let it run unsupervised overnight?

take up to hours at a time to run, so Claude is « monitoring » tasks most of the tim

How is Claude monitoring them for hours? Claude runs out of context and extremely long sessions are prohibitively expensive even according to Anthropic (after they dispense with the marketing bullshit of long running tasks)?

Not Google. Microsoft, of all companies started this project: https://open-ui.org/ when Google was busy breaking the web web components, hardware APis etc.

Google was very, very, very late to the project and of course immediately trampled all over it like they did with all the web standards.

Apple isn't holding back progress on that. They are all in on it, though they do tend to be more cautious than the "break fast and lose things" Google.

Are there any other Operating Systems than iOS, Android or Android flavors?

I remember a gov.uk team presentation. They had a usecase of someone using a PS Vita to access a government assistance program because that was the only device they had access to.

Among 450 million people in the EU there are definitely more OSes than just latest versions of iOS and Android.

for the machine, it'd make it easy to add in new tests because the function+tests are in the same context window

Given how many useless unit tests Codex just loves to write, no, thank you.

Thankfully, its training data completely misses this. So at least for now it completely ignores doctests (at least in Elixir).

Basically anything you see out of a window, anything in the street more than a few meters away from a camera, almost any overhead shot, any wide shot, any panorama or landscape, blood, liquids, glass, any semblance of stunt work, most signs, boats, any action on water, flight... is vfx

While many of the things tou say are true, movies like PHM and other "predominantly practical" movies have so many effects that they put Marvel to shame.

I highly recommend the 4-part essay series "'No CGI' is just invisible CGI" https://youtube.com/playlist?list=PLgdTaHO8FLEve_XFiRBEcOSkR...

Planes also don't fly that far

Article:

> In less than a week, the United States and NATO have pushed more than 17,000 antitank weapons

Please do go on quoting literally the same sentence:

--- start quote ---

NATO have pushed more than 17,000 antitank weapons, including Javelin missiles, over the borders of Poland and Romania, unloading them from giant military cargo planes so they can make the trip by land to Kyiv, the Ukrainian capital, and other major cities.

--- end quote ---

Strange how the totally prepared FOR YEARS special operations were left scrambling to deliver enough weapons before projected logistics collapse.