The Economics of Using AI to Churn Out Code Are Looking Worse Than Ever

Anthropic updated an estimate for how much developers will spend on its AI coding tool, signaling that the tech is only going to get costlier.

Futurism
I was testing squadrats in the last week, because I was fascinated by the idea of discovering your sourrunding. Nice app for sure, but I didn't want to share my data with more companies.
So I decided to vibecode my own solution to display my local saved fit file "squadrats".
Unfortunately, I cannot do any more changes by Claude to this code, because it always exceeds the amount of free tokens, aaaaargs.
But I am fine with the result at the moment
#running #vibecode #claude #runnersofmastodon #lcars #tng
20% done with the review of a 2.5 kloc #rstats script for a paper and I have axed about 25% of it. There are 10 kloc in other scripts that are full of bloat but not going to bother with them - it is really bad #rstats architecturally but it works numerically #AIslop #vibecode
20% done with the review of a 2.5 kloc #rstats script for a paper and I have axed about 25% of it.
There are 10 kloc in other scripts that are full of bloat but not going to bother with them - it is really bad #rstats architecturally but it works numerically #AIslop #vibecode

What's a good rule of thumb for differentiating on sight vibe coded bullshit from projects that simply leverage AI in some capacity? Discuss.

#askfedi #ai #vibecode #bullshit

@hkrn

Idiots should not #vibecode

I don't know what guardrails cursor has, as Claude code is my thing.
In my workflow, I have claude.md which contains operational directives including backups and docs.

NO COMMAND GETS EXECUTED WITHOUT MY AUTHORITY.

My vibecoding sessions consist (after issuing the prompt) of 1-40 consent commands for every single command that Ai executes.
1. Don't do it
2. Execute blah blah
3. Stop (where I can amend/seek explanation then proceed)

At every step Claude explains what it is doing, I constructed my .md this way.
Sure it may burn more tokens, but I have an idea of the process.

The code monkeys got lazy.
Lesson learned I expect.

@knowprose

Idiots should not #vibecode

I don't know what guardrails cursor has, as Claude code is my thing.
In my workflow, I have claude.md which contains operational directives including backups and docs.

NO COMMAND GETS EXECUTED WITHOUT MY AUTHORITY.

My vibecoding sessions consist (after issuing the prompt) of 1-40 consent commands for every single command that Ai executes.
1. Don't do it
2. Execute blah blah
3. Stop (where I can amend/seek explanation then proceed)

At every step Claude explains what it is doing, I constructed my .md this way.
Sure it may burn more tokens, but I have an idea of the process.

The code monkeys got lazy.
Lesson learned I expect.

@peter

Ust because you have a bot coder

Doesn't free you from being a programmer (or more specifically system analyst/architect).

NB. You can use Ai for that too.
Using AI is a learned skill

#vibecode

@InfoSecSherpa

I was initially to be super dismissive to the article.

I have seen far too many allegedly "professional" #infosec practitioners being irresponsible towards the new threat vector AND attack surface #Ai offers. But the article is solid IMHO

I will just add, that some top end corpo #vibecode devs use software platform simulacra to test against, including security...presumably

This vibecoding is actually kind of fun.

#vibeCode #copilot