Arthur Bodera

@theo Cool and normal 😅

Claude Code now throws an error if you use it to try and analyze the Claude Code source

@theo Holy system prompt!

I've held my sub for awhile because of use cases like this. Amazed it just...refuses now? I think I'm actually gonna cancel

Idk if they made other changes, but I almost exclusively use Claude Code for fixing things on my system and now it's refusing to do that? 🙃

@triketora @openclaw gpt-5.4 with xthink is similar intelligence as opus4.6, however it has less agency and likes to stop a lot, explaining what it's about to do.

reluctantly switched to openai for @openclaw today and my claw seems to have lost quite a few iq points and i’ve had to take away a lot of its responsibilities

@krispuckett @openclaw @claudeai you mean 5.3-codex? Everyone uses gpt-5.4 (and -mini). With xhigh the 5.4 intelligence is similar to opus4.6. The problem is agency - gpt routinely over-explains and then stops every few tools calls saying "I will do X now", and requires waking. Haven't found good workaround yet

Anyone else using @openclaw with Codex? How is it compared to @claudeai ? Seriously considering canceling Max plan now.

Just FYI @theo you are "flagged" (in case you still had hopes for having claude support in t3-code)

@steipete @davemorin I'm finding gpt-5.4 behaving very passively, over-explaining and stopping a lot compared to opus4.6. Is there a good guide on how to improve it? (maybe before OC supports the `phase` api-level param)

woke up and my mentions are full of these Both me and @davemorin tried to talk sense into Anthropic, best we managed was delaying this for a week. Funny how timings match up, first they copy some popular features into their closed harness, then they lock out open source.

@Pranit x.com/abodera/status…

Anthropic is burning customer goodwill over something they already know how to fix They price every API call to the cent but won't tell subscription users what their plan actually buys People can accept tighter limits What they can't accept is being told they all started using Claude wrong on the same day People are reporting 40% of their Pro limit gone in 2 prompts. Full weekly allowances drained in 19 minutes. Single-word messages eating 1-4% of sessions That is not a context window problem. It's a transparency problem Anthropic is precise where it benefits them and vague where it protects them The API pricing page is exact: Opus 4.6 runs $5 per million input tokens and $25 per million output. Every call metered The subscription page says "more usage" and "5x or 20x more usage than Pro" More than what? Anthropic has never published how many tokens each plan gets You can see what percentage of your limit you've used, but you can't see what the limit actually is. And you have no way to verify that what you're getting today is the same as last month When Codex users started hitting rate limits faster than expected, OpenAI reset everyone's limits while they investigated. They said they didn't fully understand why and chose the cautious path Anthropic's response was to tell paying users to downgrade - Switch from Opus to Sonnet - Turn off extended thinking - Cap your context at 200k instead of the 1M they advertise - Start new sessions instead of resuming old ones In short, 'this is a skill issue' Every one of those is a feature people are paying to access Paying users should not have to reverse-engineer what their plan buys If Anthropic wants to rebuild trust, the fix is straightforward - Publish actual token budgets per tier, the same way they already do for the API - Show what each message costs against the budget - Let people verify for themselves whether the deal changed They already do this on the API side. The choice not to do it for subscriptions tells you everything

@bcherny @jxnlco I can see openclaw cache efficiency for most sessions exceeding 90%, which is often higher than Claude. I don’t get the reasoning here…

Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.

I know @theo @ThePrimeagen that you’re sick of covering this, but this might be actually the end of the road 💀

Breaking: ⁦@AnthropicAI⁩ will clamp down on openclaw and other harnesses even harder. Is this the final nail in the coffin for non-enterprise users?

@theo x.com/abodera/status…

@theo This video is almost too timid. I've been hitting my limits on (on max20) about 2-3x faster than 2 weeks ago, without much changes to usage patterns/harnesses. Twitter is full of similar reports.

We need to talk about the Claude Code rate limits

@mchulet Same. Everyone is reporting the same thing ...

I'm on a MAX plan, and now I'm hitting my limit every couple of hours. What's going on? Honestly, this makes Claude unusable. I've had to sign up for ChatGPT again just because of this.

@XFreeze You forgot about bait+switch lowering subscriptions' token allowances over last 2 weeks, with everyone running out in fraction of the time...

> be Anthropic > run by doomers who literally think humanity is a plague > mass-suspend any account you don’t like for literally zero reason > entire business model: "we tell you exactly what code to write, how to use it, and how to breathe, peasant" > absolutely despise open-source AI and dedicate entire divisions to strangling it in the crib > because you can't stand the idea of code you don't explicitly own and control > “accidentally” leak your own Claude source code on npm in the biggest tech own-goal of the decade > immediately panic, DMCA the entire planet, and nuke the accounts of anyone who even looked at the link > act like digital North Korea on bath salts Nothing screams "we own you and will destroy you if you disobey" quite like punishing your own users for your incompetent leak 🤡

@KuittinenPetri @svpino It’s nerfed. It runs through a gateway/proxy with much smaller context size and i/o limits than what the models allow.

@svpino Why nobody is not even mentioning GitHub Copilot? Even the relatively cheap $10/month Pro plan gives you 300 premium prompts/month. This gives you 100-900 prompts/month + unlimited for the free models. See screenshot.

I'm on a MAX plan, and now I'm hitting my limit every couple of hours. What's going on? Honestly, this makes Claude unusable. I've had to sign up for ChatGPT again just because of this.

@MichaelGannotti @svpino @MiniMax_AI 200k context and lots of hallucinations 😬

@svpino I signed up for the @MiniMax_AI Max Highspeed plan and no issues not to mention all what you get for $80 monthly platform.minimax.io/docs/token-pla…

@MilksandMatcha I’m working on novel ways of using llms for digital preservation of old games by transpilation while retaining 1:1 functionality.

Giving away 5 Codex Pro plans Each person will get 3 months of free Codex Pro (highest tier). Winners will be selected from comments in 48 hours, comment below why you want it.

97% session usage on Claude Code. Rate limited again. On a cancelled $200/month Max plan that I'm still paying for until April 25. Meanwhile Anthropic is leaking their entire Claude Code source code through npm. Future models exposed. Employee god mode exposed. Rate limiting paying customers into the ground while accidentally shipping your entire codebase to the public. Anthropic is having the worst week in its history. Source code leaked. Claude Opus 4.6 unusable. Customers cancelling. And still no official statement on any of it.

@devneeddev x.com/abodera/status…

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. @alexalbert__ is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

Is @claudeai going to release a “Pro Max” tier soon, or fix the underlying issue 🤷‍♂️