Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude: Elevated errors across all models – Resolved

status.claude.com

Post reply on HN
Print view View original

241–250 of 275 posts

Re: Claude: Elevated errors across all models – Resolved

#241

Post by uhuhuhuhuhuh »

customguy wrote: post #216
uhuhuhuhuhuh wrote: post #209

Earlier quoted context omitted.

This inspired me to add a "No AI-isms" section to my CLAUDE.md, which has cut the typical claude-flavored tells a lot in recent sessions. Roughly: - No preamble validation or self-flagellation: "You're right to push back", "That's on me", "I appreciate you pressing on this", "I should have caught that sooner". When I correct you, say what's actually true and move on. One short "you're right, X was wrong" is the ceili…

I vouched for your comment not because I think this is or isn't helpful advice (I have no idea), but just to thank you for the concept of "narrating the shape of one's own answer". It's something that often annoys me, though I'm sure I often do it myself, but I never thought about what it is, exactly, I just filed it under the generic category of bloat.

It's genuinely useful in speech, which is why a lot of people do it. A listener can't scroll back, and it buys you a second to think. In writing both of those things go away and it becomes pure bloat.

I wonder if these emerged from models being trained on a lot of transcribed talks and videos?

Re: Claude: Elevated errors across all models – Resolved

#242

Post by weitendorf »

Sivart13 wrote: post #69
luciana1u wrote: post #23

three hours without Claude and I've relearned vim, read two man pages, and almost remembered why we used to write comments in code

If anything Claude writes too many comments. Instead of clean code it dumps walls of text describing a given 'if' as a 'user-grained access-gated control-correcting flow-valve'.

It’s interesting how deep-fried LLMs are getting the more post-training they receive.

They’re undoubtedly getting much smarter overall, but also much weirder. Before they were just trying to model our behavior, only really having us to learn from.

Now they’re literally spending thousands of years writing bash scripts in some kind of Sisyphean dreamscape, talking to each other about Goblins and Seams and smoke tests, and coming back as idiot savants.

I don’t even try to police how Claude talks or works anymore. Best practice used to be to nudge them towards whatever part of the distribution of behavior you think they should exhibit in a particular situation, because they were role-playing what a human in a particular situation would do, and if you didn’t tell them how to do it they’d just role play something worse. Now the inclination to do things the way they learned it in Agent University is so strong, they’ll literally spend more tokens re-assuring themselves and you that they are Doing It Your Way, and reminding themselves not to do give in to temptation, than you could ever prompt out of them. They’re going to spend your money thinking about goblins anyway so just let them

Re: Claude: Elevated errors across all models – Resolved

#243

Post by __turbobrew__ »

Sivart13 wrote: post #69
luciana1u wrote: post #23

three hours without Claude and I've relearned vim, read two man pages, and almost remembered why we used to write comments in code

If anything Claude writes too many comments. Instead of clean code it dumps walls of text describing a given 'if' as a 'user-grained access-gated control-correcting flow-valve'.

I have specific instructions in my AGENTS.md to always ask when adding comments. Same with tests, agents love to spew pages and pages of useless tests so I tell the agent to ask me about test cases.

Re: Claude: Elevated errors across all models – Resolved

#244

Post by shimman »

Sivart13 wrote: post #69
luciana1u wrote: post #23

three hours without Claude and I've relearned vim, read two man pages, and almost remembered why we used to write comments in code

If anything Claude writes too many comments. Instead of clean code it dumps walls of text describing a given 'if' as a 'user-grained access-gated control-correcting flow-valve'.

Gotta pump up those usage numbers pre-IPO somehow.

Re: Claude: Elevated errors across all models – Resolved

#245

Post by winrid »

km144 wrote: post #59
hmokiguess wrote: post #27

I'm gonna guess it found the smoking gun and saw the full picture then it decided it was too load-bearing for its seams to continue biting the costs.

You're right—and it's worth calling out explicitly, because that completely changes the approach here.

Here's the part worth knowing - it's only going to get worse.

Re: Claude: Elevated errors across all models – Resolved

#246

Post by Natfan »

jckahn wrote: post #233
hexasquid wrote: post #191

Earlier quoted context omitted.

Let me verify one thing. Let me read this rather than answer from memory. Let me check instead of handwaving the details. Let me confirm rather than blindly trusting. Let me ground it in evidence rather than guess. Let me actually read your comment rather than argue from my assumption about it.

You joke, but this is _exactly_ what I want Claude to be doing.

"Let me [x]" is a common phrase i've found in glm5.2

specifically, at the end of one thinking block, it said "Let me go."

Re: Claude: Elevated errors across all models – Resolved

#247

Post by hangrybear666 »

chrystalkey wrote: post #205
teitoklien wrote: post #172

Earlier quoted context omitted.

I do the same with deepseek-v4-flash + opencode triggering via mcp those terminals again by sending tmux keystrokes of Newline to those sessions and a custom setup i keep ready for these Its automated with voice mode, so i dont even need to write commands, click a button say on voice + use a picker to select which terminals to do this for , Boom Done , I use it for other interesting scenarios too

This sound all so insane I cannot tell if it is satire. I mean no disrespect, this is just as bewildering to me as private jets.

It would only make sense to me if Jensen Huang had hand delivered me some glue to sniff prior to reading the comment. Otherwise no chance.

Re: Claude: Elevated errors across all models – Resolved

#249

Post by hangrybear666 »

damienmeur wrote: post #7
PUSH_AX wrote: post #2

This is bad, I've forgotten how to code.

I rely so much on these, the ROI on having a max 90 claude plan + pro 90 codex plan is way higher than haing one solo 180 plan on a single one. It allows to derisk the issue, and also as they both kind of generous with quota reset when issues happens on their side, and it happens a lot, you get in the end way more tokens

Since anthropic gives you 35x and openai 70x of the api rate in tokens, you could surely call that ROI just not the type they want for their IPO

Re: Claude: Elevated errors across all models – Resolved

#250

Post by pmarreck »

girvo wrote: post #179
pmarreck wrote: post #132

Earlier quoted context omitted.

We're going to use your preferred development method of TDD red-green and go at this with full belt-and-suspenders; first the belt:

God that belt and suspenders thing gives me a visceral physical reaction. Nauseating.

[dead]
Post reply on HN