GET THE MICROSLOP SHIRT: https://store.gamersnexus.net/products/microslop-parody-t-shirt and support our DATA DRAGNET campaign: https://store.gamersnexus.net...
I work with a lot of software and am seeing this everywhere - problems that would be efficiently and cheaply solved with classical approaches but are solved with slow and expensive inference.
Just recently I saw an llm call to extract a postal code from a structured input. Regex would be trivial to solve it, but the person who set it up used fking LLM. What a joke.
There was recent drama around a completely vibe coded attempt at multiplayer Daggerfall. All of the prompts were leaked into the original github repo. One of the best was when Claude was asked to change an inventory icon for a fish. Claude’s response was to create from scratch a pixel art editor just to spit out a 36x24 PNG of a rotten fish.
And these guys wonder how they can possibly be burning through literally thousands of dollars in tokens every month 🙄
I kinda wonder how they end up there. Couldn’t they have just asked the bot to make the regex code if they were already using it? I imagine I am just being fucked by my biases here cause I would already to know to ask it for that.
I can only imagine there’s a lot of people who learn programming who are unaware of a lot of principles and techniques. Everything’s a nail to them, so they make use of their hammer, which in their case is Claude or ChatGPT.
To be honest, I’ve wasted entire evenings on regex. Fuck regex. We need a replacement that isn’t an llm but fixes that archaic shit. Make it human language
Yeah, that’s fair. If you have one problem and solve it with regex, now you have two problems.
Though in this case the monthly inference budget ran out causing a system outage. I was on call, so, getting a page off hours makes me dislike the llm approach even more haha
I work with a lot of software and am seeing this everywhere - problems that would be efficiently and cheaply solved with classical approaches but are solved with slow and expensive inference.
Just recently I saw an llm call to extract a postal code from a structured input. Regex would be trivial to solve it, but the person who set it up used fking LLM. What a joke.
There was recent drama around a completely vibe coded attempt at multiplayer Daggerfall. All of the prompts were leaked into the original github repo. One of the best was when Claude was asked to change an inventory icon for a fish. Claude’s response was to create from scratch a pixel art editor just to spit out a 36x24 PNG of a rotten fish.
And these guys wonder how they can possibly be burning through literally thousands of dollars in tokens every month 🙄
PEBKAC- Use codex for images, Claude for code.
BUT that is hilarious 🤣😆🤣
I kinda wonder how they end up there. Couldn’t they have just asked the bot to make the regex code if they were already using it? I imagine I am just being fucked by my biases here cause I would already to know to ask it for that.
I can only imagine there’s a lot of people who learn programming who are unaware of a lot of principles and techniques. Everything’s a nail to them, so they make use of their hammer, which in their case is Claude or ChatGPT.
deleted by creator
Yes, they could have. Easily. They didn’t think to ask.
That’s the limitation is this LLMs, they can action if the instructions are sufficient, but layer 8 is still involved, and the l8 root cause persists.
To be honest, I’ve wasted entire evenings on regex. Fuck regex. We need a replacement that isn’t an llm but fixes that archaic shit. Make it human language
Yeah, that’s fair. If you have one problem and solve it with regex, now you have two problems.
Though in this case the monthly inference budget ran out causing a system outage. I was on call, so, getting a page off hours makes me dislike the llm approach even more haha
If being out of tokens causes an outage, you have architectural problems