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

Elevated error rate across multiple models

status.claude.com

Post reply on HN
Print view View original

221–230 of 293 posts

Re: Elevated error rate across multiple models

#221

Post by trollbridge »

cromka wrote: post #215
trollbridge wrote: post #189

Earlier quoted context omitted.

oh-my-pi is a bit of a cross between the two; comes with basically everything OpenCode does, but still easy to customise. OpenCode is nice if you don't want to do a lot of research and just want to get started right away. The OpenCode Go plan for $5 a month for your first month is a great way to do this, with good models to choose from and reasonable usage limits for a beginner.

I use Go plan precisely with Opencode IDE (and also Jetbrains IDE suite), but now also have access Gemini Pro and Claude Pro. And wonder which tooling to invest my time into, especially that MCP servers also potentially come into play here, and I want at least some models/tools to handle private tasks, like handling my increasingly-complex Home Assistant setup. And I also want to start using models according to needs…

I use “all of them”. My primary harness is oh-my-pi. I probably use 10 different models on a regular basis.

I occasionally use OpenCode.

I try to use Codex and Antigravity as much as I can, often using it as a secondary agent (due to different usage pricing models than API). The same skills and MCPs work across harnesses.

Edit: I don’t use Claude Code simply because I already have enough to deal with and don’t see a major advantage to their harness. I use Opus credits from my Google subscription on the rare occasion I need them.

Cursor is also worth checking out particularly at the $20 a month price tier. If you have Grok you effectively already have it too.

I expect to have a completely different answer a year from now. The main “lift” we’ve gotten from AI tools is our clients now get an Android + iOS app + macOS app + Electron + PWA to go with whatever web based app they want us to build, at essentially the same original price. (There’s also a CLI and a TUI, but so far none of them care about that…)

We just made the decision to start adding MCPs to apps. Gonna be an interesting conversation in a few weeks when I can tell my business contact he can use his favourite chatbot to now plug in directly to the custom app he bought from me.

Re: Elevated error rate across multiple models

#222

Post by Schiendelman »

fearmerchant wrote: post #40
mdrzn wrote: post #4

The rainbow has to keep being a rainbow. ClaudeCode still has a 99.27 % uptime ClaudeCowork has 99.52 % uptime ClaudeForGovernment has 99.93 % uptime

I must be unlucky because I'm in that .73% way more than .73% of the time.

That's how outages on very popular systems work - there's no downtime when most engineers are sleeping, since they're not under load.

Re: Elevated error rate across multiple models

#223

Post by Schiendelman »

root-parent wrote: post #48
hk__2 wrote: post #21

Earlier quoted context omitted.

It’s 36°C outside, I’d rather stay inside.

>> It’s 36°C outside Yeah AI Data Centers do that....

I really wish people wouldn't pretend these actually matter compared to, say, the proliferation of personal internal combustion cars, or shipping using bunker fuel.

Re: Elevated error rate across multiple models

#224

Post by pluralmonad »

arbll wrote: post #218
tovej wrote: post #181

Earlier quoted context omitted.

Bullshit. There's plenty of big projects that don't suggest you curl a script right into your shell. If you have curl, you're probably on Linux. Just use the package manager like an adult.

The "like an adult" is what has and will continue to hold back linux on the desktop. Always gatekeeping less technical users instead of acknowledging adoption and ease of use are critical.

Is this stance gate keeping users? Isn't a pkg manager installation also a one liner? This seems more like gate keeping lazy distributors.

Re: Elevated error rate across multiple models

#225

Post by coder543 »

agentdev001 wrote: post #184
zipy124 wrote: post #162

Earlier quoted context omitted.

They are different models. OpenCode is trying to be a claude code/codex replacement, where-as pi is something you build yourself, kind of trying to be an emacs type thing compared to vs-code. As in emacs it is more common to write your own extensions, where as in vs-code most people just download them.

I keep butting into the question of; why opencode, when you've got codex available? Codex is open source as well, and i can't seem to picture a situation where one would want Opencode over Codex. As far as I can tell, they tick the same boxes- but one has the support of a big boy model provider.

Well, the reason is simple: over the past several months, it has become very difficult to use Codex with non-OpenAI models. They removed the old edit tool that didn't require OpenAI's free form tool calling (that no other LLM host supports), they are adding tools to every request of a type that break most LLM hosts unless you use a proxy to filter them out, they add a "developer" role to some messages which breaks some chat templates, etc.

If someone wanted to fork Codex and make a community-maintained version that supports third party models, that would be great, because I liked Codex better than OpenCode for the most part.

Maybe you've found workarounds. Maybe you're using an old version of Codex. Maybe you have your own soft fork. I don't know. But I used to be able to use Codex with self-hosted models, and I gave up on that about a month ago as they kept breaking that.

Re: Elevated error rate across multiple models

#226

Post by KyleTheDev »

Schiendelman wrote: post #222
fearmerchant wrote: post #40

Earlier quoted context omitted.

I must be unlucky because I'm in that .73% way more than .73% of the time.

That's how outages on very popular systems work - there's no downtime when most engineers are sleeping, since they're not under load.

A lot of deployments are also being done by engineers, performing the deploys while awake. Thus increasing the risk of outages while I'm awake. :(

Re: Elevated error rate across multiple models

#227

Post by epistasis »

cromka wrote: post #138
yanis_t wrote: post #18

I suppose it's a good time to encourage people trying out pi[1] with any cheap model from the openrouter rankings page[1]. [1] https://pi.dev/ [2] https://openrouter.ai/rankings

Is pi better than opencode?

I haven't tried opencode, but when I opened pi I was able to complain about that silly and stupid left-padding that LLM TUIs have started using that prevents basic copy-paste operation, and pi was able to edit itself to fix it.

So I'm sold on that level alone. Good stuff.

Re: Elevated error rate across multiple models

#228

Post by arbll »

pluralmonad wrote: post #224
arbll wrote: post #218

Earlier quoted context omitted.

The "like an adult" is what has and will continue to hold back linux on the desktop. Always gatekeeping less technical users instead of acknowledging adoption and ease of use are critical.

Is this stance gate keeping users? Isn't a pkg manager installation also a one liner? This seems more like gate keeping lazy distributors.

A lot of those scripts are wrappers around package managers. Creating them is extra work for distributors, but they still do it because package-manager installs are not truly one-liners and offer far less control over the installation experience.

Users need to figure out which of the 10+ package managers they should be using, then run several commands. If something fails, the error messages are often cryptic and not easily configurable by the distributor.

And that’s before getting into the many rough edges of package managers. Most of them flat-out refuse to handle configuration and leave that part to the end user. Now you also need to document how to edit YAML and restart a systemd service. With an install script this is also solved.

For power users, this always looks trivial. In practice it raises the barrier to entry and can meaningfully affect adoption if your product is often used by less technical people.

Re: Elevated error rate across multiple models

#229

Post by cyberax »

NekkoDroid wrote: post #206
mik3y wrote: post #59

Earlier quoted context omitted.

I am genuinely curious what it tells you, as "curl https//.. | sh" has long been an enormously popular approach to distribution in the open source world. Homebrew, to name just one example, advertises a similar method. (pi.sh also documents other install methods, like `npm`, on their homepage) If trust and security is the issue, unfortunately "better" ideas like hashpipe [1] never achieved critical mass [1] https://n…

I really hate the `curl | sh` specifically because if your connection drops at a specifically unlucky point in time you are left with a partially executed script which if you are unlucky enough may just have been executing `rm -r ~/.cache/ /download` but it stopped at `rm-r ~/`. Is it likely? No. Can it happen? Yea. Just make it `curl -o && sh ` and this entire problem is gone.

Most scripts now put all the code into a shell function and call it in the last line of the script, so this bug can't happen.

Re: Elevated error rate across multiple models

#230

Post by sergiotapia »

yanis_t wrote: post #18

I suppose it's a good time to encourage people trying out pi[1] with any cheap model from the openrouter rankings page[1]. [1] https://pi.dev/ [2] https://openrouter.ai/rankings

I can vouch for ohmypi, it's quite good out of the box and works great with your codex subscription or openrouter or fireworks etc. Very good harness.

https://omp.sh/

Post reply on HN