You know, with a bit of prompting, you can instruct Gemini to output the state of the conversation into a prompt that you can enter in a new chat and continue where you left off. But now with a fresh context window.
It’s incredible how forgiving you guys are with Anthropic and their errors. Especially considering you pay high price for their service and receive lower quality than expected.
At least personally, it feels like the choices are
the one that's okay with being used for mass surveillance and autonomous weapons targeting, the one that's on track to get acquired by the AI company that dragged its feet in getting around to stopping people from making child porn with it, the one that nobody seems to use from Google, and the one that everyone complains about but also still seems to be using because it at least sometimes works well. At this point I've opted out of personal LLM coding by canceling my subscription (although my employer still has subscriptions and wants us to keep using them, so I'll presumably keep using Claude there) but if I had to pick one to spend my own money on I'd still go with Claude.
It's still night and day the difference in quality between chatgpt5.4 and opus 4.7. Heck even on Perplexity where 5.4 is included in Pro vs 4.7 which is behind the max plan or whatever, I will pick sonnet 4.6 over the 5.4 offering and it's consistently better. I don't love Anthropic, I don't have illusions about them as a business.
It's fairly small issues for an amazing product, and the company is just a few years old and growing rapidly. Also, they are leading a powerful technological revolution and their competitors are known to have multiple straight up evil tendencies. A little degradation is not an issue.
What's the alternative? Are you suggesting other LLM providers don't charge high price? Or that they don't make mistakes? Or that they provide better quality?
We're talking about dynamically developed products, something that most people would have considered impossible just 5 years ago. A non-deterministic product that's very hard to test. Yes, Anthropic makes mistakes, models can get worse over time, their ToS change often. But again, is Gemini/GPT/Grok a better alternative?
If you have a good product, you are more understanding. And getting worse doesn't mean its no longer valuable, only that the price/value factor went down. But Opus 4.5 was relevant better and only came out in November.
There was no price increase at that time so for the same money we get better models. Opus 4.6 again feels relevant better though.
Also moving fastish means having more/better models faster.
I do know plenty of people though which do use opencode or pi and openrouter and switching models a lot more often.
> It’s incredible how forgiving you guys are with Anthropic and their errors.
Ironically, I was thinking the exact opposite. This is bleeding edge stuff and they keep pushing new models and new features. I would expect issues.
I was surprised at how much complaining there is -- especially coming from people who have probably built and launched a lot of stuff and know how easy it is to make mistakes.
The consumer surplus is quite high. Even with the regressions in this postmortem, performance was above the models last fall, when I was gladly paying for my subscription and thought it was net saving me time.
That said, there is now much better competition with Codex, so there's only so much rope they have now.
At the time you wrote your comment there were 4 other comments and all of them very negative towards the Anthropic and the blog post in question here. How did you get this conclusions?
Confused as well, I rather supposed Antrophic had some standing for saying no to Trump and being declared national security threat, but the anger they got and people leaving to OpenAI again, who gladly said yes to autonomous killing AI did astonish me a bit. And I also had weird things happening with my usage limits and was not happy about it. But it is still very useful to me - and I only pay for the pro plan.
> Anthropic staff told us OpenClaw-style Claude CLI usage is allowed again
Anthropic staff have had contradictive statements in Twitter and have corrected each other. Their intent for clarifications lead to confusion.
> OpenClaw treats Claude CLI reuse and claude -p usage as sanctioned for this integration unless Anthropic publishes a new policy.
Oh cool, so everything is back to business now, until they all or sudden update their policy tomorrow that retracts everything.
Anthropic have proved themselves to be be unreliable when it comes to CC. Switching to other providers is the best way to go, if you want to keep your insanity.
It's the PayPal model of customer service: they'll ban you at any time for any reason or none at all, but if you're very nice they might be willing to have a human look at that decision at some point, but probably not.
Straight up PayPal and Venmo can go to hell. They banned my account, I painted a gun for a guy with a cerakote bale-on setup. He paid with PayPal and they banned me. His gun, just a legal service to paint it.
I pulled our company portal away from PayPal when they refused to restore my account.
Five years later, I tried to re-activate and the human I finally got to effectively told me to fuck off; so I will spend the rest of my life bashing that trash company at every chance.
They had this on here since day 1 of the block. This is just Openclaw saying "if you run Openclaw inside Claude Code, it's compliant with the Anthropic ToS", because, well, it's literally running inside Claude Code.
What's not allowed is grabbing the oauth tokens and using these for your own custom agent, which is what was (and still is) banned.
Nothing has changed, this appears to just be a giant misunderstanding (and probably a poor choice of words from Openclaw).
But there was a period of time when using Openclaw via Claude Code (via -p) was not allowed and it even gave an error message in that case. That's why people find the constantly changing messaging confusing.
The most recent Anthropic announcement was not that people would be banned for using subscriptions with OpenClaw, but that it would be charged as extra usage. I think the reason this was changed three days after that announcement is that being charged for extra usage meant people would not be banned for using their subscription OAuth tokens directly against the Anthropic API with a third party harness, as they had been before. But rather both that usage, and the more recent claude -p usage both be charged as extra usage.
I don't see anything on this page that claims something different from that, or that addresses that claim at all.
They need to stop announcing this on freaking Twitter and make a formal announcement on their blog, this is ridiculous and unprofessional. Make a policy decision and stick to it, and dictate how alternative harnesses should work.
> until they all or sudden update their policy tomorrow that retracts everything.
Oh no. They won't update the policy. Boris or Thariq will casually mention in a random off-hand commebt on Twitter that this is banned now, and then will gaslight everyone that this has always been the case.
you know how s bunch of IT people are trying to "escape the permanent underclass" well it seems like anyone building their tools on cloud providers is doing the opposite. theyre willingly bexoming the underclass in hopes it trickles down
> Switching to other providers is the best way to go, if you want to keep your insanity
I remember when I’d periodically rage quit from Uber One to Lyft Pink and back again every time I had a terrible customer-service experience. In the end, I realized picking a demon and getting familiar with its quirks was the better way to go.
I’m currently sticking with Claude, in part because I’m not exposed to this nonsense due to OpenClaw, in larger part because of the Hegseth-Altman DoD nonsense. More broadly, however, I’m not sure if any of Google, Anthropic or OpenAI are coming across as stars in AI communication and customer service.
With Uber and Lyft or even Anthropic versus OpenAI versus <insert flavor of the month here> I don’t even try to attach myself to any one brand.
It’s so easy to switch between all of them. I can open the Uber and Lyft apps and compare in a minute. I can run Claude and ChatGPT in parallel and see which one gets a better handle on the question. I can switch LLM providers with a few minutes of signing up for one and cancelling the other.
They all try to encourage brand lock in but it’s easy to pick up and move if you’re using them for their main service.
reply