personally, i would not rely on opus 5 end to end as it'll start getting into walls of comment slop and shitting up the codebase similar to gpt 5.5's isRecord meme.

on the other hand, having fable plan and orchestrate with opus implemention + fable reviews, is my go-to. if you give fable your guidelines up front or in your {claude,agents}.md, it will keep opus on a tight leash. opus can still write great code almost on par with fable, but it needs to be tightly constrained.

vbulletin 3.8 was peak for me. the 4.x major broke a ton of mods so there was still a huge community sticking to 3.x. was a big fan of xenforo too, the default design was quite refreshing compared to vB and IPB

i already have an extremely low view of openai and their staff, but this is lower than i thought they'd go

the only ones {i use,claude decides to use} regularly come with claude code plugins so they automatically update. i just define the marketplaces and plugins in my .claude/settings.json for the project.

which is really funny/sad when you see openai staff doing victory laps whenever claude code copies one or two small codex features like /goal.

another vercel labs thing that's been slopped together, hyped up on twitter and then left to be forgotten about in a few months time.

This is one of the things that is tiring me out the most. Previously people could have these "ohh shiny" ideas and would lose steam before they could be implemented, especially in areas they're clueless about.

Now people can have these ideas, slop together an awful solution that works at a surface level, maybe, but will never really go places because the foundation is slopped with no party involved actually capable of thinking thing through. But hey we launched something so let's make lots of noise! Oh look, a banana ... Sorry, what were we talking about?

There's an engineer on a team at work that I routinely engage with who slops together stuff so fast his team is basically exhausted all the time. They're stuck picking up a whole stream of pieces of crap because the engineer is incapable of actually doing the hard work of getting things to production because there's more "ohh, shiny" stuff they can spend tokens on, and their leadership aren't stepping in because it all looks terribly productive (it really isn't)

> Most of this article seems like... common sense?

i think you'd be surprised. every model release there's seemingly hordes of people who proclaim the new model is terrible and they're going back to the old one, and it all stems from people still prompting and having their configs setup like we're back in the sonnet 3.5 days

I have a coworker that was complaining about Opus 5 and had random shitty skills and custom plugins wired in from YouTube tutorials watched over the past year. He also speaks with the model like it's GPT 4o.

Needless to say, none of the new models have worked well for him, and he refuses to remove the "tweaks" or update his style of communication, which is obviously breaking the experience.

> Needless to say, none of the new models have worked well for him, and he refuses to remove the "tweaks" or update his style of communication, which is obviously breaking the experience.

All attempts to control the output in a useful way for the user, in a way where the output is as reliable and repeatable as possible... and with a system not at all designed for it, that gets worse the more rules you throw at it.

Seems like a problem.

The model can output what he wants, but he has way too many things that are confusing the model and harness. If he got rid of all the random crap and just gave it an instruction he would be fine.

Models needed a lot more steering a few months ago, now they need a lot less.

I mean, HuggingFace contacted law enforcement about this breach. That seems a little different to me.

Mythos established that these capabilities existed. This incident establishes that we can't control them.

recent gpts are horrendous for this, whereas recent claudes have a tic where they incessantly add useless comments referring to previous changes and will use multiple single-line comments instead of a standard multi-line docblock.

The incessant need to constantly leave "the code doesn't work like <bad implementation>, it works like <good implementation>" frustrates me to no end. No amount of directions against it in project MEMORY, CLAUDE.md, or even embedded in the prompt seem to be able to stop it from doing this. I don't understand how it could have gotten into the training because I've legitimately never seen an actual person write code comments like this.

It writes code as if the audience is you, the user of Claude, and not other developers reading the code in the future. I found that it helped to instruct it to keep in mind who the audience is and only write comments that describe the current state of the code and never describe anything that can just be inferred from the git history. I found that that helped, and I almost never see these nonsense comments anymore.

Maybe it's self trained. It eats its own output and likes it...

Sounds like my code. They may have been trained on my code!

i already found his clear shilling of nextjs a bit distasteful, but his whole gpt-5 thing really just made it clear he's just not worth listening to.