At least with Codex, this has not been my experience at all. It still screws up sure, but in every case I can ask "why did you do this" and it can trace back what made it take that particular decision. Typically it's always that I either didn't specify the problem correctly or made a really dumb mistake (executing the task on the wrong project....did this one yesterday) or it's something within a skill file that instructs it (at which point I fixup the instructions).
Once in a blue moon it's actually the model making a material error in it's thinking and I have to go back and redo it.
agreed to some extent. I think this parody still highlights what I feel is often the experience. It might not happen on a simple task such as changing a button color, but on more complicated things, this can definitely be exactly what it feels like.
Claude is great, but I have come to really hate the way it "talks". It's so irritating and there seems to be no way to make it speak normal English. So many claudisms in every response
It's a joke like the endless conservative dudes doing the "ordering coffee" joke is. It relies upon the ignorance of the viewer -- which is usually a fair assumption -- and basically that your understanding of something is based upon the prior accrued layers of "jokes".
Haha this is spot on how I've been feeling lately. I find it unbearable to work with this model for this reason... any trick out there you can do to steer it not to overcomplicate things? I guess Codex here I come
This got me on "cyanide blue", and I was ROLLING ON THE FLOOR LAUGHING on "Approaching usage limit". I can barely stop laughing now and my stomach hurts. I mean, Thank You!
I only made it through the first round of prompt selection; both options for the second step were equally pointless and not at all prompts I would ever expect to result in a constructive outcome. In my experience, telling the model it screwed up without specifically addressing, unambiguously, how to fix it, only leads to more suffering. If this page illustrates nothing else, I think it shows the immense downside of trying to use simple one or two sentence prompts.
EDIT: Actually, I used to use Google's AI Studio a lot and fork it after every successful prompt interaction. When I'd encounter a problematic issue like this, I'd revert to the previous fork and try a different prompt until I could get the desired outcome, thus mitigating the need to "argue" with the LLM. Unfortunately the ability to cleanly fork and revert everything including the LLM context was removed some months ago, and I've yet to discover a workflow with any tool that works as well for me.
> In my experience, telling the model it screwed up without specifically addressing, unambiguously, how to fix it, only leads to more suffering.
I wonder if this is just a reflection of some senior folks being arrogant towards junior folks. When the latter finished a task but not to the liking of the senior person they might just get a "that's wrong, try again". Just to have sth similar repeat the second time around. But the arrogant guy got to boss around the junior one, and some junior folks grow up learning that's how you should behave so they also do it later.
Now it's not a person but a machine. And people just make fun of the dumb machine. Well, garbage in, garbage out If you are not specific in what you want, you might get crap back. Or at least sth you didn't envision.
- The people who won't make any effort to learn the tools, and something as simple as reverting code (via git) needs to be done by AI?
- The awful programmers who we've had to endure working with, who are so bad at simple changes that they have negative productivity?
- Or Claude itself?
---
BTW: I don't have these problems, but I'm also not afraid to do things myself when it's easier.
Edit: If I want to change a button's color, I just change it manually. If I don't know where the code for the button is, I might start with prompting, (because AI can often find the code faster than I can,) and then once the diff is proposed, start adjusting things by hand.
To be fair I’ve worked on human programmed systems where similar “it should be a half point story” requests would be met with snark by the engineers and take 2 sprints.
So this site is just a fan-fiction that thinks it's somehow dunking on Claude? I've never had a session that remotely resembles any of this. I honestly can't tell what point this site thinks it's making.
I wrote my own harness to stop shit like this from getting to my attention out of frustration.
I'm sure there's quite a bit of variation from person to person in these sorts of experiences, based on your harness, the way you talk, the stored memory, your CLAUDE.md, etc. But people absolutely have had this Opus 5 style experience the app simulates.
Yeah, I don't mind using AI to help me at work, but having to "talk" with this stupid crap all day will send me to an early pension or something. Can't be healthy in the long run.
Exactly! Never thought of it, but now that you say it. You know, like when you talk to a person in a neutral environment and without asking you just know that they are a school professor for example, because of the way they express themselves. Now I wonder what imprint Claude leaves on us.
P.S. I have utmost respect to school professors by the way. My mum is a retired prof and I see it firsthand in many of her colleagues too. I guess explaining same things multiple times a day and talking to kids for 8 hours straight objectively creates some recognizable speech patters and habits.
I’ve never used any of these tools. Please tell me that this is a grossly exaggerated parody, and that the tools don’t write like this, or do so many ridiculous things. For my sanity.
(I am genuinely uncertain, though I presume it’s at least somewhat exaggerated.)
> Please tell me that this is a grossly exaggerated parody, and that the tools don’t write like this, or do so many ridiculous things
It's a pisstake, but (in the bits I read, and based on my own personal experience) the writing style is barely exaggerated, while the behaviour doesn't ring true at all.
Ok, I can't describe this, but my toes curled at the prompts, I was literally yelling at the screen. "None of these prompt options do what I want, they're going to make it WORSE!"
And yes, yes they did. The prompts options aren't ... diagnostic shaped? Some seem like they'd actually push the agent away from the solution.
One day we'll have proper theory of this and we'll laugh at people putting in magical input that obviously can't work.
Alternately models will get smarter and can read the problem space better despite the prompt, instead of because of it.
(edit: to be fair, I don't actually use opus 5. Opus 4.6 is best opus. )
I use Opus and Sonnet 5 all the time and I find their language grating. But honest, I prefer to put up with it and get the results than to put up with my own human limitations and not get the results.
I heard this was a thing when listening to a Theo podcast, he mentioned to add a "Only use subagents if the user explicitly requests them" line in your agents.md file.
I don't know if it works, but I've always had a consistent level of token burn on my plans (I've only heavily used Sol after adding it).
I dunno, in my experience it's often overly-narrow, sometimes jumping through all kinds of hoops to preserve some edge-case behaviour that doesn't matter because I didn't mention it could be changed.
I was expecting it to spend 30 minutes running headless chrome instances, taking screenshots and analyzing them in python to verify the blueness of the result.
Nails the Claude dialect. Technical nonsense like:
> I'm collapsing this back to the rendered outcome:
And intermixed with SaaS product page idioms from a brain-damaged marketer like:
> No broader cleanup.
> No further architecture work.
> Just the button.
Aside from the patterns everyone knows like em-dashes, "its not X, it's Y", etc. I think the key features of claude diction is it sounds like a junior engineer over their skies who is trying to make up for that with extra verbiage mixed with extremely grating SaaS marketing-ese.
Am I the only one whose experience doesn't match this?
My gripe with Claude is that while investigating how to do this it will report 200 other incidental findings which I overlooked and I realize those are broken too and need urgent fixing, derailing me, not it.
Oh man, exactly. I'm very prone to scope creep as I work on tasks. I already would notice some things that could be fixed or refactored and have a hard time not touching them before I used agents. But now I have to be very intentional about not letting it manipulate me into fixing EVERYTHING RIGHT NOW. Half the time the "one more thing worth noting, unrelated..." isn't even an actual issue, it just brought it up to fish more usage out of me.
Also, while this little demo is certainly exaggerating the issue, I do find working with Claude to sometimes get quite verbose and tiresome. I doubt I would struggle this much to get it to change a button color, but the patterns of speech, the endless lists, the over-explanations, and the whole song and dance of trying to get it to make the change you want without side-effects is frustratingly familiar to me.
Just when I came back to my pc and was thinking "I hate this world were everyone talks about AI like fanatics" this made me a little bit happy, especially the unhingend all caps options towards the end
Once in a blue moon it's actually the model making a material error in it's thinking and I have to go back and redo it.
To the people rather lamely doing the "it's satire/a joke", that would require this to be an exaggeration of a reality. But...it isn't.
This got me on "cyanide blue", and I was ROLLING ON THE FLOOR LAUGHING on "Approaching usage limit". I can barely stop laughing now and my stomach hurts. I mean, Thank You!
EDIT: Actually, I used to use Google's AI Studio a lot and fork it after every successful prompt interaction. When I'd encounter a problematic issue like this, I'd revert to the previous fork and try a different prompt until I could get the desired outcome, thus mitigating the need to "argue" with the LLM. Unfortunately the ability to cleanly fork and revert everything including the LLM context was removed some months ago, and I've yet to discover a workflow with any tool that works as well for me.
I wonder if this is just a reflection of some senior folks being arrogant towards junior folks. When the latter finished a task but not to the liking of the senior person they might just get a "that's wrong, try again". Just to have sth similar repeat the second time around. But the arrogant guy got to boss around the junior one, and some junior folks grow up learning that's how you should behave so they also do it later.
Now it's not a person but a machine. And people just make fun of the dumb machine. Well, garbage in, garbage out If you are not specific in what you want, you might get crap back. Or at least sth you didn't envision.
- The people who won't make any effort to learn the tools, and something as simple as reverting code (via git) needs to be done by AI?
- The awful programmers who we've had to endure working with, who are so bad at simple changes that they have negative productivity?
- Or Claude itself?
---
BTW: I don't have these problems, but I'm also not afraid to do things myself when it's easier.
Edit: If I want to change a button's color, I just change it manually. If I don't know where the code for the button is, I might start with prompting, (because AI can often find the code faster than I can,) and then once the diff is proposed, start adjusting things by hand.
I guess we are all PMs now.
I'm sure there's quite a bit of variation from person to person in these sorts of experiences, based on your harness, the way you talk, the stored memory, your CLAUDE.md, etc. But people absolutely have had this Opus 5 style experience the app simulates.
P.S. I have utmost respect to school professors by the way. My mum is a retired prof and I see it firsthand in many of her colleagues too. I guess explaining same things multiple times a day and talking to kids for 8 hours straight objectively creates some recognizable speech patters and habits.
(I am genuinely uncertain, though I presume it’s at least somewhat exaggerated.)
It's a pisstake, but (in the bits I read, and based on my own personal experience) the writing style is barely exaggerated, while the behaviour doesn't ring true at all.
It’s funny because there are elements of truth in each bit of it, though.
And yes, yes they did. The prompts options aren't ... diagnostic shaped? Some seem like they'd actually push the agent away from the solution.
One day we'll have proper theory of this and we'll laugh at people putting in magical input that obviously can't work.
Alternately models will get smarter and can read the problem space better despite the prompt, instead of because of it.
(edit: to be fair, I don't actually use opus 5. Opus 4.6 is best opus. )
but still.
I use Opus and Sonnet 5 all the time and I find their language grating. But honest, I prefer to put up with it and get the results than to put up with my own human limitations and not get the results.
This hit a bit too close to home. Sol has the same issue, spawns a lot of agents for no good reasons (besides burning tokens).
I don't know if it works, but I've always had a consistent level of token burn on my plans (I've only heavily used Sol after adding it).
I use codex now.
But you can see in this thread that folks definitely have experienced this.
"I was wrong" and "the honest truth" are just forever phrases that are now dead to me.
> I'm collapsing this back to the rendered outcome:
And intermixed with SaaS product page idioms from a brain-damaged marketer like:
> No broader cleanup.
> No further architecture work.
> Just the button.
Aside from the patterns everyone knows like em-dashes, "its not X, it's Y", etc. I think the key features of claude diction is it sounds like a junior engineer over their skies who is trying to make up for that with extra verbiage mixed with extremely grating SaaS marketing-ese.
My gripe with Claude is that while investigating how to do this it will report 200 other incidental findings which I overlooked and I realize those are broken too and need urgent fixing, derailing me, not it.
Also, while this little demo is certainly exaggerating the issue, I do find working with Claude to sometimes get quite verbose and tiresome. I doubt I would struggle this much to get it to change a button color, but the patterns of speech, the endless lists, the over-explanations, and the whole song and dance of trying to get it to make the change you want without side-effects is frustratingly familiar to me.