> The coding agents got really good It's since november 2025, the so called "inflection point", that I'm still wondering for who coding agents become "really good". All I observe they got better at tool call and answering questions about big codebases, especially if the question has a vague pattern to search, and they're superuseful for that! For generating production code even with a lot of steering and baby sitting…
> Absolutely not, not quite there not even close in my experience.
Well... I don't know what you expect but so far I'd like all my colleagues to write code at the level of what I get from codex.
What on earth do you mean? I live near an area with lots of pelicans. If you look up at one flying overhead this is what they look like. Here is a photo for comparison: https://commons.wikimedia.org/wiki/File:American_white_pelic...
Sure, something like that. Note like the examples you posted.
I've very confused. The SVGs show the beak, wing, tail, feet and body as though viewed from directly underneath.
They look similar to the photo, but meet the instructions better ("from underneath").
My own informal test when generative AI came out has been "a picture of an old man riding a bicycle over a river". I just ran it for chatgpt with the standard model I have (5.5). It shows the old man on an old bicycle with the bicycle on a slack line and the slack line extending over the river with a medieval village in the background. The point is that the prompt has a subtle ambiguity - "how is the old man going ov…
> but they still fail add the assumptions that people would draw. I have mixed feelings about this. I agree with the default assumptions you have as to "what people would draw", however what do you want from this cognitive automation? Do you want, "what most people would do" or do you want "something creative, an outlier, that still satisfies conditions" ?
Well, if Rene Magritte or some similar artist produces a man riding a bicycle over a tightrope, he's being because he knows what people expect from "a man riding a bicycle over a river" but I think the machine doesn't know the normal expectations and so it's not being creative, just failing. A splatter sheet of an industrial painting operation may look like a Jackson Pollock print. The hired painters might even notice this after their shift. But if the process that produces this is just painting tractors, it's not creative either.
okay hold my beer. both claude and codex running now. EDIT: both agents took about 20 minutes. I used that exact prompt in a clean directory for each, and then said "deploy to netlify" - so a total of two prompts. Codex: https://astounding-bavarois-27b5a2.netlify.app Claude: http://strong-hotteok-91dfb0.netlify.app Netlify is having trouble claiming the Claude project, so if you need a password it's "My-Drop-Site" FY…
Frogger is kind of too well known such that there is ample training data for building that specific game. The game I was thinking of is relatively obscure -> Panel de Pon
Yes I was surprised at the time that it failed so badly at Frogger, I think from memory it was colission detection it just couldn't get right, plus the positioning of various game elements as it has quite a lot going on (the examples above still have some problems with these things). I thought there would be open source examples out there in js/html but perhaps not so much for frogger.
I remember this very clearly myself. Before opus 4.5, I was doing a lot of hand holding and was coding a lot myself, but I have not written code since that day more or less. I did write some stuff myself just to learn how the enigma encryption machine worked, so wrote myself to learn. But professionally, I stopped coding in November.
How do you justify your salary given that you're just using a tool that any of us could use for $20 an hour in your role?
I wonder how much the 'inflection point' is a thing vs marketing. I'm sure the models got somewhat better, but even now when I'm trying to 'vibe code' a game with the latest models (combination of Codex w/ gpt5.5 and gpt5.3-codex), they really do struggle. They definitely get something barebones up and running, but it's far from a fully fledged application.
It's very real but probably very domain specific. It got really good at a lot of traditional web dev stuff, bash, sql, and writing one off scripts to accomplish random tasks (hence all the agent stuff taking off). And they got good at staying on task. That may not translate to game dev because from what I understand a lot of these gains are basically around post training methods driven by synthetic data generation etc (with potential caveats on how synthetic that data actually is lol). I wouldn't be surprised if the areas of code the llms are good at now are straight up just product decisions of where to allocate budget for generating those synthetic data sets, and game dev stuff might not be at the top of the list because the customer base for that might not be as big
I wonder how much the 'inflection point' is a thing vs marketing. I'm sure the models got somewhat better, but even now when I'm trying to 'vibe code' a game with the latest models (combination of Codex w/ gpt5.5 and gpt5.3-codex), they really do struggle. They definitely get something barebones up and running, but it's far from a fully fledged application.
It is all marketing. The easiest way to tell is that a year ago the same people said the inflection point was X or Y model. When people claim LLMs just don't work for them, the first question is whether they're using the latest model or not, and if not, dismissing the poster. The thing is that that same question was being asked a year ago, and even a year before that, but with the models that lead to a dismissal toda…
My take is there was one big inflection point around opus 4.5 when they got the agentic stuff working and now whether or not it works depends on whether your use case/area of software engineering is profitable enough for the companies to have spent a bunch of money generating synthetic data to RL on, or if it's similar enough to areas that they've done that for. With similar enough being a very loose constraint given how much overlap there is in a lot of coding fundamentals. Tbh if the models aren't working for you now I don't think they're gonna be working for you in 6 months
I think it's because both sides are talking about different things. If you go in expecting it is good enough to make developers obsolete today(reasonable impression to get from the way a lot of people hype it) you would be disappointed and after first couple of tries every few months you would probably not try it much with next generations. Reasonable if it's considered a dichotomy. But a lot of people excited about…
You're completely twisting what I said. I've never talked about people claiming it's not making developers obsolete. We are obviously extremely far from that. I'm talking about people who say it doesn't work to build basic features in their projects correctly. Just take a look at this comment on a different topic, which lists all the pre-requisite for those AI models to work well, from the perspective of someone who…
That's a list of like 6 things. And each of those less complicated a question then the seven thousand questions people throw at you when you complain about something not working right on a Linux distro or about speeding up build times for a new tool or configuring webpack or like pretty much any software tool. What lint rules are you using are you using poetry or uv are you running on Mac windows linux or wsl how are your security groups configured in aws - some tools are more plug and play but it's quite the stretch to say that asking "how is your code organized, do you have your agents.md config file set up, do you have tests, and how large is the codebase" is some sort of unmanageable list of questions for a software engineer to think through when figuring out wtf is going on with some new tooling they're using
My own informal test when generative AI came out has been "a picture of an old man riding a bicycle over a river". I just ran it for chatgpt with the standard model I have (5.5). It shows the old man on an old bicycle with the bicycle on a slack line and the slack line extending over the river with a medieval village in the background. The point is that the prompt has a subtle ambiguity - "how is the old man going ov…
> but they still fail add the assumptions that people would draw. I have mixed feelings about this. I agree with the default assumptions you have as to "what people would draw", however what do you want from this cognitive automation? Do you want, "what most people would do" or do you want "something creative, an outlier, that still satisfies conditions" ?
Reminds me of that dad teaching their kids programming by preparing a PB sandwich [^0].
Solvers are generally really good at bending your rules, but in a context where you want that. An outlaw rule-bending maniac is not what I want from a helpful agent.