Hacker Newsnew | past | comments | ask | show | jobs | submit | gck1's commentslogin

There's no chance they're able to subsidize this much. You can burn $600 of API equivalent in a day without affecting your weekly quota that much.

What's likely is that light users are paying for heavy users and API pricing is heavily inflated.


There's nothing consistent with Anthropic on this matter.

Their documentation, cli, SDKs, TOS, their public stance - have major contradictions and are subject to so much interpretation that you can't really figure out what's allowed and what's not.

Opencode allowed? No

Custom agentic harnesses allowed? Yes

Opencode is a custom agentic harness? Yes, but not allowed

Which agentic harness is allowed? Can I use a custom agentic harness I develop - say, tmux that runs claude code? We don't know, but you'll know if we ban you


Anthropic itself advertised their own implementation of agentic loop (Ralph plugin). Sure, it worked via their official plugin, but the end result for Anthropic would be the same.

There's nothing in TOS that prevents you from running agentic loops.


And please, find an alternative to discord for your community.

It baffles me that everyone has collectively decided it's a great idea to have discussions on a platform which is not indexable, and has no usable search even when you're in it.


SQL - somewhat, python - no. LLMs that write code only work well with proper guardrails. Dynamic languages like Python lack essential guardrails.

Once the project can't fit in model's usable context window (~150k tokens even for 1M models), you need code fighting back and leaving breadcrumbs for model to follow.


It seems like everyone has a very different idea of what spec means in agentic coding.

To me, spec answers the what, the plan answers the how, and in what order, build packets answer the how but with more granularity.

In most cases, you should only care about the what. How it gets done (plan) is simply an implementation detail that you should not care about the same way automated tests should not care about them.

What you prescribe in spec is that data must pass from A to B through C, preserved in D and presented in E in shape of F. It's much easier to write (and change) this in spec than in say, Rust.


ccusage on my $200 subscription shows that I'd spend ~$600 per day if I used PAYGO model.

Not sure how accurate this is, but found contextarena benchmarks today when I had the same question.

It appears only gemini has actual context == effective context from these. Although, I wasn't able to test this neither in gemini cli, nor antigravity with my pro subscription because, well, it appears nobody actually uses these tools at Google.

https://contextarena.ai/?showLabels=false


Claude is Anthropic's property which they rent to the government. Is there any other place where rental agreements don't come with clauses on how the property can and can't be used?


Enforce this with deterministic guardrails. Use strictest linting config you possibly can, and even have it write custom, domain specific linters of things that can't happen. Then you won't have to hand hold it that much


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: