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

Anthropic made a mistake in cutting off third-party clients

archaeologist.dev

Post reply on HN
Print view View original

231–240 of 255 posts

Re: Anthropic made a mistake in cutting off third-party clients

#231

Post by oooyay »

wiether wrote: post #212
bambax wrote: post #206

Earlier quoted context omitted.

> The best thing for consumers would be if all these model providers strictly provided usage-based API pricing Using openrouter myself I find the costs of APIs to be extremely low and affordable? I don't send the whole codebase to every question, I just ask about what I need, and everything is actually ridiculously cheap? $20 lasts about 3 months.

I tried to plug CC on my OpenRouter account, and just asking it what my project was doing (a directory containing three .sh of around 100 LOC each), I saw like 20 API requests to OpenRouter accounting for almost $1 in total. Meanwhile copy/pasting those shells in OpenRouter's Chat and asking the same question resulted in a single API request costing a tenth of a cent. I could probably try tuning everything to keep co…

I don't actually think Claude Code is very good and this is exactly why. It's not really optimized to use its tools efficiently. I think Cursor probably does a better job of that but I imagine all of these coding assistants will come with some form of local tooling support in the way of vector DBs etc one day.

Re: Anthropic made a mistake in cutting off third-party clients

#232

Post by gempir »

dionian wrote: post #94
vorpalhex wrote: post #66

Earlier quoted context omitted.

OpenCode has some more advanced features and plays nicely in more advanced setups. ClaudeCode isn't bad at all, but OpenCode has some tricks up it's sleeve.

e.g. ?

- ships also as a desktop app

- ships with web server that has a UI you can open in your browser, even access remotely with tailscale or so

- the server has an API to do almost all things allowing you to build on top of it, the people at ramp build a very advanced internal agent on top of OpenCode https://builders.ramp.com/post/why-we-built-our-background-a...

Re: Anthropic made a mistake in cutting off third-party clients

#233

Post by runjake »

albert_e wrote: post #209
submeta wrote: post #197

Earlier quoted context omitted.

> symlink CLAUDE.md -> AGENTS.md and run `codex` instead of `claude`. This is simple and beautiful. Thank you for sharing it :)

indeed! is there a way to do this on windows?

Don’t. No need to symlink. Just add “@AGENTS.md” to your CLAUDE.md.

Re: Anthropic made a mistake in cutting off third-party clients

#234

Post by pacoWebConsult »

bloppe wrote: post #105
ojosilva wrote: post #28

They did not. Anthropic is protecting its huge asset: the Claude Code value chain, which has proven itself to be a winner among devs (me included, after trying everything under the sun in 2025). If anything, Anthropic's mistake is that they are incapable of monetizing their great models in the chat market, where ChatGPT reigns: ie. Anthropic did not invest in image generation, Google did and Gemini has a shot at the…

> Also Opencode makes it all easily swappable It's all easily swappable without OpenCode. Just symlink CLAUDE.md -> AGENTS.md and run `codex` instead of `claude`. > they are working hard on making it impossible for other models to support their every increasing agent feature set (skills, teleport and remote sessions, LSP, Chrome integration, etc). Every feature you listed has an open-source MCP server implementation,…

Models each have their own, often competing, quirks on how they utilize AGENTS.md and CLAUDE.md. It's very likely a CLAUDE.md written for use with Claude Code utilizes prompting techniques that results in worse output if taken directly and used with Codex. For example, Anthropic recommends putting info that an agent must adhere to in statements like "MUST run tests after writing code" and other all-caps directives, whereas people have found using the same language with GPT-5.2 results in less instruction following, more timid responses than if the AGENTS.md were written without them.

Re: Anthropic made a mistake in cutting off third-party clients

#236

Post by sinenomine »

noosphr wrote: post #182
lvl155 wrote: post #179

Earlier quoted context omitted.

This is really not the point. Anthropic isn’t cutting off third-party. You can use their models via API all you want. Why are people conflating this issue? Anthropic doesn’t owe anyone anything to offer their “unlimited” pro tiers outside of Claude Code. It’s not hard to build your own Opencode and use API keys. CLI interface by itself is not a moat.

People should take this as a lesson on how much we are being subsidized right now. Claude code runs into use limitations for everyone at every tier. The API is too expensive to use and it's _still_ subsidized. I keep repeating myself but no one seems to listen: quadratic attention means LLMs will always cost astronomically more than you expect after running the pilot project. Going from 10k loc to 100k loc isn't a 10…

There are high-quality linear or linear-ish attention implementations for the scales around 100k... 1M. The price of context can be made linear and moderate, and it can be greatly improved by implementing prompt caching and passing savings to users. Gpt-5.2-xhigh is good at this and from my experience has markedly higher intelligence and accuracy compared to opus-4.5, while enjoying lower price per token.

Re: Anthropic made a mistake in cutting off third-party clients

#237

Post by blumenkraft »

isoprophlex wrote: post #111

I want them to cut off these electron wrappers. If there's no tokens going to these third parties, the more they can keep subsidizing my claude code usage.

Please stop with this 'subsidising' nonsense. It is nobody's business whether anybody is subsidizing anything. I couldn't care less what the internal financial mechanics of Anthropic is. Even if they are losing money on every single paying user, I DO NOT CARE, it's their problem, not mine.

Re: Anthropic made a mistake in cutting off third-party clients

#238

Post by theahura »

I wrote a response here (https://news.ycombinator.com/item?id=46602206) but TLDR, no they didn't. These third-party clients are competitors and capitalists. They raised money from institutional investors, and are trying to get Anthropic to subsidize their growth, which Anthropic is not at all obligated to do. One could maybe argue that this was an honest mistake, but then you probably shouldn’t have a file called ‘anthropic_spoof.txt’ in your repo with the line “You are Claude Code, Anthropic’s official CLI for Claude”, which you then use to bypass oauth.

I think these third party clients put their customers at risk. Most of them likely did not realize that the tools were doing something that violated ToS. Using these tools put many of those users at risk of account bans and risk Anthropic pulling the plug entirely and raising prices, which would be bad for everyone

Re: Anthropic made a mistake in cutting off third-party clients

#239

Post by Dylan16807 »

ozim wrote: post #215
Dylan16807 wrote: post #193

Earlier quoted context omitted.

I'm sure everyone "wants to" land a many million dollar deal with a big company that has mild demands, but that doesn't mean those naggers are bad customers. Bad customers have much more annoying and unreasonable demands than a pricing sheet.

I don’t think anyone lands contracts with “mild demands”. Most of the time you want to cut off ‘non customers’ as soon as possible and don’t leave ‘big fish’ without having direct contact person who can explain stuff. People just clicking around on their own will make assumptions that need to be addressed in a way no one wastes time.

> Most of the time you want to cut off ‘non customers’ as soon as possible

If you mean this literally, one of the best ways to turn non-customers into customers is to give them a way to pay you. Which means telling them the price. If you're implying something else by ‘non customers’ then I'm missing the implication.

> and don’t leave ‘big fish’ without having direct contact person who can explain stuff

You can give a contact person and have a list of prices.

> People just clicking around on their own will make assumptions that need to be addressed in a way no one wastes time.

Making everyone call you to negotiate is going to waste time.

Re: Anthropic made a mistake in cutting off third-party clients

#240

Post by blumenkraft »

Majromax wrote: post #171
dchftcs wrote: post #74

Earlier quoted context omitted.

Anthropic and OpenAI are essentially betting that a somewhat small difference in accuracy translates to a huge advantage, and continuing to be the one that's slightly but consistently better than others is the only way they can justify investments in them at all. It's natural to then consider that an agent trained to use a specific tool will be better at using that tool. If Claude continues to be slightly better than…

In that case though, why the lock-in? If the combination really does have better performance than competitors’ offerings, then Anthropic should encourage an open ecosystem, confident in winning the comparison.

I imagine they do not see it as a level playing field. If OpenCode can draw on Claude Code credits but cannot draw on Codex ones (we've just had a tweet promising to fix this, more or less), then it can be construed as an advantage on the part of OpenAI. Personally I think it's idiotic and companies should stop penny-pinching in situations where people are already paying $200, there can be no more value extraction at this price point.
Post reply on HN