A nice chance to try sonnet again, must say, I'm not missing the load bearing assumptions, honest read of the permission matrix, what's genuinely a Django convention and what's a design choice, what's worth my thinking, and what's worth being precise about.

Long story short, it seems to be faster and less vocal but not much dumber (it's just my thinking partner, so I read a lot of the output as I create a large data model).

▲

devin 17 hours ago | parent | next [-]

Reading this made me ill. Nice job!

	▲	teekert 16 hours ago \| parent [-]
		My allergy to Claudish is also rapidly progressing. I think it’s now at a boundary that is genuinely worth exploring. Oh no!

▲

martinald 17 hours ago | parent | prev | next [-]

The other bizarre word I've now noticed and can't understand is "pathological". As in "bug has turned pathological"

▲

lachlan_gray 16 hours ago | parent | next [-]

In old school ML a pathological solution is often a collapse of some kind due to an underspecified objective. Maybe one parameter explodes or the model predicts "0" for everything

I read this as "the code is working as intended but the bug is an artifact of the original design"

	▲	martinald 6 hours ago \| parent [-]
		I genuinely have no idea what it is meant to mean in the context it uses it. Load-bearing etc is annoying but roughly understandable, some of the opus5 classics are completely out there. I'm a native English speaker as well, I shudder to think what a second language speaker would do (even if they were very confident with the language!).

▲

evanmoran 16 hours ago | parent | prev | next [-]

The new ones for me are adding extra terms like the 3 faces, to park at the door. (It’s 3 methods that block the thread)

▲

devin 16 hours ago | parent | prev | next [-]

"Latent" is another one, as in "latent bug" or in one particularly odd case "latent twin".

▲

Waterluvian 16 hours ago | parent | prev [-]

This is a term fellow devs have been using for years and years and my brain just cannot come to re-index its meaning. So I am immediately distracted by the context switch to sociopathic liars and related psychology.

▲

Waterluvian 16 hours ago | parent | prev | next [-]

Has anyone else had luck having a system level prompt for “express all responses in bullet point form unless full sentences are specifically necessary”? Because I’ve been having tremendous luck with that.

	▲	visarga 16 hours ago \| parent \| next [-]
		I'm doing the opposite - prose. And specifically for Claude the 4s - "simple short synthetic style"
	▲	nater5000 16 hours ago \| parent \| prev \| next [-]
		Just over the last couple of days I've found that forcing the models to use bullet points has helped a ton. I was even tempted to post something/ask around if others had any similar experiences with this.
	▲	chuckadams 16 hours ago \| parent \| prev [-]
		I remember Jetbrains Junie which read like that all the time. Never used first-person either. I've not used Jetbrains AI for a while though, not sure if it still reads that way.

▲

nonethewiser 17 hours ago | parent | prev | next [-]

Way leas capable of taking high level instructions and making sensible changes across a codebase.

Good for more precise changes.

▲

estetlinus 15 hours ago | parent | prev | next [-]

That definitely reframes it

▲

Syntaf 17 hours ago | parent | prev | next [-]

I've almost entirely stopped using Opus 5, at least with Sonnet I know what i'm getting -- Fable for the complex stuff and Sonnet for the precision changes.

The verbosity of Opus 5 isn't even my issue, it's consistency. For every 10 tasks Opus 5 accomplishes, there's at least one task that Opus 5 does just an atrocious job of, or a debugging investigation that it just completely goes off the rails on.

▲

jason-phillips 15 hours ago | parent | prev | next [-]

While you're in there, it may be worth a pass.

▲

doawoo 15 hours ago | parent | prev | next [-]

this is like poetry

▲

echelon 17 hours ago | parent | prev [-]

My engineering has changed so much that I'm now using this time to catch up on emails and think about design and architecture for the next leg of work. (And post on HN, of course.)

I would never have predicted this a year ago.

I always scoffed about engineers not doing work during Github outages - I'd always find some kind of other engineering to do if PRs or builds were piling up.

But during model outages, and since I'm not actively set up to use OpenAI/Codex at the moment, I'll just find something else productive to do. I don't think I'm ever going to write code by hand again unless I'm fixing something the AI can't manage or the change is small enough. Why even try when the machine is 100x faster?

Should I give Codex another try? It's been a month or so since I last used it, and it always felt inferior at Rust and TypeScript.

	▲	r_lee 16 hours ago \| parent [-]
		I think if you've got the money, you should set up a coding harness that you can plug to openrouter and then be able to switch quickly, as these new models seem to be coming out pretty regularly now switching subs is kind of a PITA since you need to commit to a month at least