Terrasque

I found out the hard way this is not entirely correct, as a user found a valid json that yaml parsers didn’t handle. IIRC it was some exotic whitespace issue

Management: “But the coin miners are the only ones maintaining the server, if it wasn’t for that it would have died long time ago”

Well, it wasn’t a comment on the quality of the model, just that the context limitation has already been largely overcome by one company, and others will probably follow (and improve on it further) over time. Especially as “AI Coding” gets more marketable.

That said, was this the new gemini 2.5 pro you tried, or the old one? I haven’t tried the new model myself, but I’ve heard good things about it.

Yeah, I’ve been seeing the same. Purely economically it doesn’t make sense with junior developers any more. AI is faster, cheaper and usually writes better code too.

The problem is that you need junior developers working and getting experience, otherwise you won’t get senior developers. I really wonder how development as a profession will be in 10 years

Working on a big codebase, I don’t even get the idea to ask an AI, you just can’t feed enough context to the AI that it’s really able to generate meaningful code…

That’s not a hard limit, for example google’s models can handle 2-million-token context window.

https://ai.google.dev/gemini-api/docs/long-context

AI isn’t ready to replace programmers, engineers or IT admins yet.

On the other hand… it’s been about 2.5 years since chatgpt came out, and it’s gone from you being lucky it could write a few python lines without errors to being able to one shot a mobile phone level complexity game, even with self hosted models.

Who knows where it’ll be in a few years

Svn: 20 October 2000

Git: 7 April 2005

I remember using svn when git development was started

which is about exactly as old as git.

Wdym by that?

Or a few more gb of LLM?

I was trying to find an article I read about a year ago, about an experiment where AI was assisting a doctor. Where it suggested questions and possible diagnosis for the doctor to look into.

IIRC the result was both faster and more accurate diagnosis. Too bad I can’t find it again now :(

You’re not great taking medical advice from a doctor either, seeing how often they’re wrong.

I remember back in the day this automated downloader program… the links had a limit of one download at a time and you had to solve a captcha to start each download.

So the downloader had built in “solve other’s captcha” system, where you could build up credit.

So when you had say 20 links to download you spent some minutes solving other’s captchas and get some credit, then the program would use that crowdsourcing to solve yours as they popped up.

And just to top it off, make this pythonscript a dialect of rust

🫰🤙🫵👌✊🫳🫸🤲🤌

I worked on one where the columns were datanasename_tablename_column

They said it makes things “less confusing”

I mean, I totally agree with you. But that also kinda ignores all the useful things a dog can be trained to do.

So you’re saying it’s already feature complete with most json libraries out there?

https://y.yarn.co/00b19fc5-cc98-4af3-8298-93092ffc4ff6_text.gif

Yep, I usually make docker environments for cuda workloads because of these things. Much more reliable

It can be surprisingly helpful. I needed a small program to change between three “states”, two separate programs that use the gpu and can’t run at the same time that I run on a server, and an “idle” state where none of them are running. And a simple web ui to check and change state.

This was the conversation: https://chat.openai.com/share/661322bc-2bd2-4608-9c7f-ec6d9f488601

Note that it did mess up the transitions code a bit, but it was easy to fix after a brief look at the documentation. However, the http page worked 100% straight off the bat, and the flask code and running of the commands worked perfectly. It’s not a big thing, but a lot of “boilerplate” code and double checking docs was avoided. And this is the free tier.