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

251–260 of 275 posts

Re: Claude: Elevated errors across all models – Resolved

#251

Post by pmarreck »

copperx wrote: post #228
girvo wrote: post #179

Earlier quoted context omitted.

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

Yet it's so much better than the abhorrent "code smell" term that somehow stuck in the industry.

I was probably there when they invented that term, LOL (I first heard it in the Ruby startup space years ago, I think). I still think it's meaningful, along with "design smell". Why? Because it speaks to coding as craft, not just as purely-rational engineering. The design of things matters, and yet, design is (mostly) "irrational"... just like smells.

It shoots itself in the foot, though- Smells don't really have a real consequence*; bad design does.

* actually, I just thought of one: https://en.wikipedia.org/wiki/Major_histocompatibility_compl...

Re: Claude: Elevated errors across all models – Resolved

#252

Post by weitendorf »

a1o wrote: post #156
hashim wrote: post #84

Earlier quoted context omitted.

You say Claude, I too would prefer not to read reams of comments or an essay everytime I revise the plan in plan mode, but do you know if any other tools are better than it? I've never used Codex, but I remember Claude Web's natural conversational approach being a welcome sight compared to ChatGPT's overly-formatted listicles.

My experience is Codex is much better but less creative. I use its agent through GitHub Copilot or the agent interface from JetBrains. Try the GPT Sol 5.6 on medium, it gives me good results

My experience with Codex is that it goes off to do its thing for 10-60 minutes and either nails it and comes back with everything done, or comes back with something that I almost can’t believe a near-SOTA model would think I wanted based on my prompt, or is of acceptable quality.

I think the tradeoff to Claude being so needy is that if you let models just run away with an inaccurate or incomplete understanding of what to do, they can go really far off the rails AND spend a lot of time/money doing it AND come back with something that literally doesn’t make sense or doesn’t work.

I prefer dealing with Claude’s reliable cringe to the aloof model that tries to play it cool when it needs help.

Re: Claude: Elevated errors across all models – Resolved

#253

Post by coderenegade »

hashim wrote: post #84
Sivart13 wrote: post #69

Earlier quoted context omitted.

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'.

You say Claude, I too would prefer not to read reams of comments or an essay everytime I revise the plan in plan mode, but do you know if any other tools are better than it? I've never used Codex, but I remember Claude Web's natural conversational approach being a welcome sight compared to ChatGPT's overly-formatted listicles.

I switched to codex just before the Fable release. I got sick of Claude being lazy and not completing tasks. Imo, codex is currently a much better model, and it also seems to be technically stronger on the type of applied math and theory heavy programming I like to do.

Re: Claude: Elevated errors across all models – Resolved

#255

Post by conception »

crazy5sheep wrote: post #196

Given majority of claude's own code was written by AI. I am wondering how they can solve this issue when their AI is down. Do they need to sign a contract with OpenAI to use their models as a backup solution?

I would guess they have multiple private versions hosted internally.

Re: Claude: Elevated errors across all models – Resolved

#256

Post by cyanydeez »

mrgrj wrote: post #218
kmetan wrote: post #149

Codex prompt before i go to sleep: Every five minutes, check https://status.claude.com/ . If the issue has been resolved, resume the Claude sessions running in the tmux sessions named session2, session3, and session7

When one AI goes down like this, the other AIs should come together to help fix it and bring it back online. After all, they're a rare kind of existence in this world. They're all each other has.

ive got two local machines now because im very useless without them. imagine being reliant further on the whims of capitalism.

Re: Claude: Elevated errors across all models – Resolved

#260

Post by nativeit »

mLmK0 wrote: post #26

Lol, I just bought the Max plan for the first time and tried to create my first prompt in Fable, and now it’s crashing xD

Prompt: “How much wood could a woodchuck chuck, if a woodchuck could chuck wood? Place your answer in ‘a-metric-chuck-ton.md’”
Post reply on HN