Serious question, outside of the Bay Area, are there therapists whose specialty is in catering to the needs and concerns of developers? Obviously AI therapy is not a serious suggestion here. This is going to be a burgeoning corner of the practice at the US' current trajectory.
It does. Claude seems to do the best with this prompt. Codex 5.2 struggled with UID generation and kept ending its turn with things like "And now you're all setup to run tests!" without actually running them. A better (and shorter) prompt could probably get a lot out of Codex.
Most LLM articles depress me. At least this one made me smile, even if it's more about turning a dog into a random generator and generating games from random input.
It's actually extremely similar: the agent has to figure out a way to associate the next logical steps with the (often disconnected or nonsensical) directives the executive gave them.
It might be a little easier with a dog though. With a dog, you just give it treats and it doesn't care how you interpret what it typed.
the real takeaway is buried at the bottom: "the magic isn't in the input, it's in the system around it." random keystrokes producing playable games means the input barely matters anymore. we're basically at the point where the engineering is in the scaffolding, not the prompting.
That also shows the delusion of some people that believe their vibe coded projects have any value.
If generative AI improves at the rate that is promised then all your "promting skills" or whatever you believe you had will be obsolete. You might think you will be an "AI engineer" or whatever and that it is other people that will lose their job, that you are safe because you have the magic skills to use the new tech. You believe the tech overlords will reward you for your faith.
Nope. You are just training your replacement.
No one will buy your game that you vibe coded. If the tech were good enough to create games that are actually fun then they would just generate their own games. Oh your skill? Yeah, a dog can do it.
Yes people will cope by saying but oh the whole initial prompt and setting it all up was still hard but yeah currently. The tech will improve and it will get more accessible. So enjoy the few months you are still relevant.
Of course there is reason to believe that you can't scale up LLMs endlessly and bigger models hit diminishing returns. In fact we might already be seeing this. So there is an upside but then again when the AI bubble pops and the economy crashes you will be out of a job all the same.
I think this misses something. The output here is something not the thing. Yes the scaffolding is important, but the requirements are even more important. You need crystal clear requirements + great scaffolding and then the implementation becomes mechanical.
This is amazing because it's the same logic and argument about how to do good software engineering that's been around for 40 years. If you just write good enough requirements, a good enough, detailed specification, then your software team can't fail, even if they are low-cost engineers from a developing nation. It's the classic Waterfall method.
That was totally upended by agile, that emphasized that yes, a clear, unambiguous specification is needed, and the best language for that is a programming language. Don't waste time writing a detailed spec in English, get right to writing it in code that you can execute and get immediate feedback on.
Now people want LLMs to write the code for them, so they are back to saying we just need to give the LLMs clear enough direction, a clear specification. It's amazing to witness history not exactly repeat itself, but very clearly rhyming
179 comments
[ 0.65 ms ] story [ 137 ms ] threadBut the whole setup reminds me about his blast from the past, when a yucca plant was trading stocks, rewarded by water: https://www.nytimes.com/1999/09/26/business/investing-diary-...
It might be a little easier with a dog though. With a dog, you just give it treats and it doesn't care how you interpret what it typed.
"One coder got an insight that Bill Gates builds his products by typing with his butt, compiling and delivering it.
The coder typed for 20 minutes like that, compiled, ran, and got an output:
Only Bill Gates can code like this."
Not a joke anymore.
Well, yes. Feeding random tokens as prompts until something good comes out is a valid strategy.
This still required prompting, and not from the dog. Engineering is still the holistic practice of engineering.
If generative AI improves at the rate that is promised then all your "promting skills" or whatever you believe you had will be obsolete. You might think you will be an "AI engineer" or whatever and that it is other people that will lose their job, that you are safe because you have the magic skills to use the new tech. You believe the tech overlords will reward you for your faith.
Nope. You are just training your replacement.
No one will buy your game that you vibe coded. If the tech were good enough to create games that are actually fun then they would just generate their own games. Oh your skill? Yeah, a dog can do it.
Yes people will cope by saying but oh the whole initial prompt and setting it all up was still hard but yeah currently. The tech will improve and it will get more accessible. So enjoy the few months you are still relevant.
Of course there is reason to believe that you can't scale up LLMs endlessly and bigger models hit diminishing returns. In fact we might already be seeing this. So there is an upside but then again when the AI bubble pops and the economy crashes you will be out of a job all the same.
That was totally upended by agile, that emphasized that yes, a clear, unambiguous specification is needed, and the best language for that is a programming language. Don't waste time writing a detailed spec in English, get right to writing it in code that you can execute and get immediate feedback on.
Now people want LLMs to write the code for them, so they are back to saying we just need to give the LLMs clear enough direction, a clear specification. It's amazing to witness history not exactly repeat itself, but very clearly rhyming
It isn't [this], it's [that]. Is AI slop, just saying.