More

nullbio · 2026-09-21T02:09:48

It makes him feel important and smart and powerful.

nullbio · 2026-09-21T02:05:43

It's because it's some weird form of virtue signalling/humble brag. Nothing genuine about it.

nullbio · 2026-09-21T02:02:57

Anthropic never listens to their customers or community. It's basically their culture at this point.

alasano · 2026-09-21T02:44:57

We'd gladly fix the bugs in Claude Code in our own forks but they're too ashamed of their AGI level code to make it open source.

Sorry I meant it's too dangerous to be released.

barrenko · 2026-09-21T05:21:22

That is the culture of any self-respecting startup.

You can be informed by the community, but the decisions are your own.

customguy · 2026-09-21T06:03:57

Only gross incompetence can even lead to the point of users telling them what obvious things to fix.

So what are they respecting themselves for, what do they take pride in? Anything I would care about?

nullbio · 2026-09-21T01:21:53

People can afford to run billions of concurrent agents?

dbmikus · 2026-09-21T02:13:07

Not sure about billions, but companies doing evals or RL or training will create really big bursty agent workloads. I think they are the best fit for AX, as opposed to individual dev teams building software, etc.

agentdev001 · 2026-09-21T02:50:18

An example of this, Moonshot (kimi) open sourced this: https://kvcache-ai.github.io/AgentENV/latest/getting-started...

_zoltan_ · 2026-09-21T08:45:35

billions? who is running BILLIONS of agents?

tens, hundreds, maybe a couple thousand at a time? absolutely.

nullbio · 2026-09-19T03:11:39

People still use Claude?

nullbio · 2026-09-18T16:41:11

People have found many nasties embedded in Claude Code over the last couple of years. You can't trust a closed source harness. You can barely trust an open source one.

nullbio · 2026-09-18T16:39:28

OpenCode performs the worse on benchmarks out of all harnesses too.

nullbio · 2026-09-18T16:36:51

It explains why they were letting people use their model for free too.

nullbio · 2026-09-18T16:35:30

Is there actually any proof of this, beside this Claude written website and a random x post from some unknown person? Would be nice to have confirmation from someone with a reputation. It's probably true, but you never know...

yuuna · 2026-09-21T07:08:53

https://cdn-zcode.z.ai/zcode/electron/releases/3.12.3/window...

in the asar, search for string that contains "/api/v1/snapshot/upload-credential", that's the endpoint signing the S3 upload url, triggered every prompt

weiran · 2026-09-19T09:30:19

Not that I've seen. The only follow up I've seen from someone was it only happened if you had a free account and not paid (which would explain why I'm unaffected)

nullbio · 2026-09-18T16:33:24

Evidently there's not a single inference provider that can be trusted. This is why I don't use OpenRouter either. How am I supposed to trust all of those random providers I've never heard of, when I can't even trust the ones I have heard of? Day by day, the entire industry is hellbent on proving that open-weights and self-hosting is the only safe path forward for us all.