Can we get a count of people that have had Claude read irrelevant documents or perform unnecessary web searches even when told not to from the beginning?

I'm starting to wonder if this increased token usage is inadvertently bleeding into how Anthropic actually trains their model, especially leading up to IPO. As older models are deprecated and users are forced onto newer models, if the default is less efficient and more token expensive that directly results in higher "profit" for Anthropic in terms of the consumption their users have to tolerate - lest they jump to a competitor.

I found Opus 4.7 to be slow and wasteful with token usage. It's shocking how inefficient it is with tasks like bash tool usage and web searching, delegating them to a dozen subagents only to get stuck and never return until you esc and intervene. That, in addition to all of the broken tooling Anthropic built in to limit token usage like the broken monitoring tool made managing Claude a chore. I was happy to pay $200/month for Opus 4.5 when they had more capacity, but 4.7 felt like a huge step back and no longer worth the price and inconvenience.

I remember an OpenAI employee comment on the GPT5.5 release post about how they specifically geared it towards long-horizon tasks and its been a breathe of fresh air in that regard. I have five two-week long sessions going right now and there's been no degradation in performance or efficiency. It's much better at carrying rules/learnings forward even in long-running sessions and grounding/refreshing itself in verified facts when it loses context.

Its funny because in two weeks I've gotten way more done with GPT5.5 with way fewer tokens and way less handholding. I think this goes to show how important tooling and the harness is and how a capable model like Opus 4.7 can be severely handicapped by bad product decisions.

https://claude.ai/settings/billing shows "Your subscription will be canceled on May 13, 2026."

For the past week even after I cancelled my renewal I was able to use Claude Design without issue and was actively working on a project through it. But starting a few hours ago, I'm now locked out with this message:

"Claude Design is available to users on subscription plans." in spite of having 3 more days of "max access."

This feels incredibly gross considering I ALREADY paid for Max 20x which includes Design access.

Also, unsurprisingly, Claude's support pages are completely broken: https://support.claude.com/en/articles/9015913-how-to-get-support

Following "Click your initials or name in the lower left corner of the Console and select “Get help” from the menu." leads to a broken flow that does nothing for me. Absolutely nothing happens when I click "Get Help".

I filed a chargeback through my credit card but I feel like others should be made aware that if you cancel your Claude subscription, you'll lose access to Design and potentially other products immediately, so back them up before doing so.

Comments URL: https://news.ycombinator.com/item?id=48084278

Points: 5

# Comments: 2

On https://claude.ai/settings/billing I see "Your subscription will be canceled on May 13, 2026."

For the past few days I was able to use Claude Design without issue and was actively working on a project. But starting a few hours ago, I'm now locked out with this message:

"Claude Design is available to users on subscription plans." in spite of having 3 more days of "max access."

This feels incredibly gross considering I ALREADY paid for Max 20x which includes Design access. I'm considering a chargeback through my credit card. Does anyone have experience getting through to their customer support? It seems like its all chatbot generated.

Comments URL: https://news.ycombinator.com/item?id=48083816

Points: 7

# Comments: 1

I finally get fed up and started using GPT 5.5 the past 4 days and its a breath a fresh air despite feeling much more minimal. With Claude I had to write so many hooks to enforce behaviors it wouldn't remember and it lacked common sense on. GPT 5.5 does a much better job with things like knowing the AWS CDK CLI can hang on long CloudFormation deployments and it should actively check the deployment status using CloudFormation API rather than hanging for 30+ minutes - and it does this all without asking.

Maybe there's better tooling built into Codex too, but at least on the surface level it seems like how smart the model is makes a significant difference because Claude has more tools than I can count and still struggles to use "grep".

Edit: Like just now - I can't tell you how many times I day I see this sequence:

"Sorry, I'll run in parallel"

"Error editing file"

"File must be read first"

Repeat 10x for the 10 subagents Claude spawned and then it gets stuck until you press escape and it says "You rejected the parallel agents. Running directly now"

"X is just Y - why is it so complicated?"

its lazy and boring to read these on every thread about a disliked big company

I'm building my own saas. I spent 6 months writing the code by hand before using Claude, and that was fine, but its much faster to give the exact specs to Claude and have 3-4 sessions working in parallel with me. When you validate changes with exact test specs there's much less correction you need to do. I always hit my weekly limit and it's far cheaper for me to use this than to hire someone and spend time onboarding them.

It's impossible to tell these days whether 4.7 is stuck because it's thinking and Anthropic suppressed all output (seriously, 4.7 will just start making changes without explaining any reasoning - how is that an upgrade?) or because the underlying infrastructure is having issues.

4.5 -> 4.7 feels like going from working with a coach-able, junior engineer that does well with clear guidance to working with a cocky mid-level that will spend too long on pointless tangents and make confidently incorrect changes without any discussion.

There's obviously a lot of physical waste in this day and age and it's arguably small by comparison, but the paper waste from mail spam still disgusts me.