Be careful getting too deep in OpenAI tooling because they end up deprecating almost everything in under two years, sometimes without even a formal notice.
Everything they make these days looks to be strongly vibecoded without a decent review or functional testing. This leads to basic avoidable bugs that annoy vast numbers of users.
Not only this, but when you point out an issue to them on GitHub, they have a history of blocking the reporting user instead of tackling the technical issue.
At this point, it’s safe to assume all net-new software is vibecoded. Who in their right mind would take a month to create an MVP when a bot can spit it out in an afternoon? Existing software isn’t necessarily immune, but there are still individuals that are fighting (or resisting the change) to keep their code base human readable. It’s a losing battle. Eventually those people are either gonna change their minds, leave or be pushed out. Then the agents will be unleashed upon those code bases too.
> Who in their right mind would take a month to create an MVP when a bot can spit it out in an afternoon
The people who need something more than an MVP, I would suppose. Bot sure does spit out a prototype faster than any human can, but actually building on that dogshit prototype becomes slower than someone with a clue writing by hand.
Makes sense. Very hard for humans to keep up with LLM-generated code. But LLMs/Agents have no problem with this. So they are using the dev style that would drive their business towards generating more money. A funny concept for a non-profit organization.
I don't see how buggy software directly leads to generating more money? A company being successful doesn't somehow magically make them infallible, 100% rational or immune to making mistakes (as you are implying).
I don't know why people keep harping on buggy software.. it really is the average not the exception. I mean we see this with all the defects in existing software that agents find.
I love how people all pretend that they and most engineers are god like programmers. Sure, some people are really good. My 30 years of experience say that is like 5%, maybe if you are at google or a really good start up, that can creep up to 30-50%.
By far the majority of engineers are not elegant or even really craftsman like. Add to this that unless you are working on a pet project you are usually neck deep in something that has had teams working in it for years.
It creates situations where most engineers don't really know what the code base does below the surface area where they are making feature changes. So work gets cobbled on or patched in where people are comfortable making changes.
All I can say is I would much rather have 3 open Opus 5.5 instances than a team of 3 working for me if we are only talking about delivering high quality code. I don't think that is the only value of engineers, but I think we are at a point where the models have way exceeded average engineer ability. There are still tendencies for "compatability everything" and "don't rock the boat" in the current frontier LLMs that can create architectural issues, but if you know what to look for when working, it isn't generally an issue.
I mean just remember how mush everyone complained about buggy games or MacOs or whatever before LLMs even came around.
I imagine the play is RL your model to solve problems using your own tools which it knows how to use most efficiently until it defaults to using services like managed agents, etc.
Be careful getting too deep in OpenAI tooling because they end up deprecating almost everything in under two years, sometimes without even a formal notice.
Everything they make these days looks to be strongly vibecoded without a decent review or functional testing. This leads to basic avoidable bugs that annoy vast numbers of users.
Not only this, but when you point out an issue to them on GitHub, they have a history of blocking the reporting user instead of tackling the technical issue.
At this point, it’s safe to assume all net-new software is vibecoded. Who in their right mind would take a month to create an MVP when a bot can spit it out in an afternoon? Existing software isn’t necessarily immune, but there are still individuals that are fighting (or resisting the change) to keep their code base human readable. It’s a losing battle. Eventually those people are either gonna change their minds, leave or be pushed out. Then the agents will be unleashed upon those code bases too.
> Who in their right mind would take a month to create an MVP when a bot can spit it out in an afternoon
The people who need something more than an MVP, I would suppose. Bot sure does spit out a prototype faster than any human can, but actually building on that dogshit prototype becomes slower than someone with a clue writing by hand.
This type of comments is making me insane.
Most people are practical
I'm so curious what you do when the providers go down. Do you tell your boss you can't fix the incident because your token quota is out?
It’s all greenfield and I’m not surprised to see deprecation. Eventually tooling will distill into what works.
Makes sense. Very hard for humans to keep up with LLM-generated code. But LLMs/Agents have no problem with this. So they are using the dev style that would drive their business towards generating more money. A funny concept for a non-profit organization.
I don't see how buggy software directly leads to generating more money? A company being successful doesn't somehow magically make them infallible, 100% rational or immune to making mistakes (as you are implying).
I don't know why people keep harping on buggy software.. it really is the average not the exception. I mean we see this with all the defects in existing software that agents find.
I love how people all pretend that they and most engineers are god like programmers. Sure, some people are really good. My 30 years of experience say that is like 5%, maybe if you are at google or a really good start up, that can creep up to 30-50%.
By far the majority of engineers are not elegant or even really craftsman like. Add to this that unless you are working on a pet project you are usually neck deep in something that has had teams working in it for years.
It creates situations where most engineers don't really know what the code base does below the surface area where they are making feature changes. So work gets cobbled on or patched in where people are comfortable making changes.
All I can say is I would much rather have 3 open Opus 5.5 instances than a team of 3 working for me if we are only talking about delivering high quality code. I don't think that is the only value of engineers, but I think we are at a point where the models have way exceeded average engineer ability. There are still tendencies for "compatability everything" and "don't rock the boat" in the current frontier LLMs that can create architectural issues, but if you know what to look for when working, it isn't generally an issue.
I mean just remember how mush everyone complained about buggy games or MacOs or whatever before LLMs even came around.
When should I use this over Codex? Is this supposed to be called by other tools/agents?
that was my assumption, maybe you use Claude but want it to use OpenAI image generation or something. this got a physical shrug out of me.
Codex = agent harness
OpenAI CLI = wrapper around API
> wrapper around API
aka curl? :-/
Curl with token usage so it’s better.
I imagine the play is RL your model to solve problems using your own tools which it knows how to use most efficiently until it defaults to using services like managed agents, etc.
Honestly surprised this wasn't available sooner.