Live data from Hacker News

Claude Code May–August 2026 weekly limits promotion

support.claude.com

241–250 of 275 posts

Re: Claude Code May–August 2026 weekly limits promotion

#241
post #73
post #31

Earlier quoted context omitted.

I think running a model unsupervised in anything above medium is a sucker move to burn more tokens. The high effort models can be great in limited context, but unsupervised they too often end up navel gazing. High doesn't always mean smarter, but it always burns more tokens. Medium and low seem to be decent for day to day tasks.

My favorite part (codex thing) is how it runs all commands twice, every time. Once on a sandbox, realizes nothing works in its sandbox, then again outside the sandbox. Fucking hell.

I just run it in dangerous / yolo mode in my own sandbox. Works great and no more nagging.

Re: Claude Code May–August 2026 weekly limits promotion

#242
post #15

prediction: extension of promotions because of the progressive move to codex.

Are there any figure to back up people moving to Codex?

I moved a while back when Claude started refusing to do security audits and also failed to run properly in my sandbox without a lot of wrangling. Renamed Claude.md to agents.md and had no problems at all. There’s almost 0 switching cost.

Re: Claude Code May–August 2026 weekly limits promotion

#243
post #127

I’m supporting you as a company , but since grok 4.6 and codex , it’s just stupid to go with your pricing model . Cursor + grok + router that uses open ai and a bit of anthropic to verify tests etc it’s a no brainer . Why should I pay you money , and have slower model and less intelligence? Oh yeah and I do not care about limits with cursor ultra at all . Unlike with you .

Cursor really is the best deal right now, the amount of usage you get with Grok is amazing and you can use frontier OpenAI or Anthropic models if you ever need to but most code can be written well by Grok.

Have you used their CLI? I run everything in VMs or containers to prevent access to things on my host.

Re: Claude Code May–August 2026 weekly limits promotion

#244

I got a max account during this promotion and it's been very fun but I'm a little burned out and am kind of looking forward to going back and tinkering with game engines without the help of an LLM for code gen (will still use it for documentation questions but I can do that with the free tier)

I too have the same experience with LLM generated code. I just get burnt out reading it and all the verbosity it has. I eventually gave up reading through it and keep it as a archive of previous work, while handwriting the code. If I get stuck somewhere, I asked the agent to generate a snippet based on my archived code and what i need to achieve and manually copy paste it.

I wish inline completions would have gotten better but it seems no effort is being put into it and it is frozen in time right now. Thankfully, the stuff i use this code for is simple and small scale. I can’t even begin to imagine how actual programmers are feeling about this.

Re: Claude Code May–August 2026 weekly limits promotion

#245
post #229

Earlier quoted context omitted.

Damn that's crazy. I put in $10 on the 5th of August and still have $1.99 left today, the 18th. I use Deepseek Flash almost exclusively.

Deepseek Flash is somewhere around the OpenAI Luna level though. That's not bad (and nor is Luna!) but Opus/Sol are just massively better especially once you start doing agentic tasks. See for example https://x.com/zainhas/status/2085567832268656755

Agreed, it's not SOTA but I'm happy with the trade off. My preference is to use mostly local models and augment them with Deepseek. It's been a pretty great equilibrium.

Re: Claude Code May–August 2026 weekly limits promotion

#246
post #79

I think the difference between the Anthropic token maximization approach (vibe code all the things!) and OpenAI's focus on efficiency, terseness and token reduction are going to be the defining features of who wins the long-term race. My money is on the more efficient solution. Even if Anthropic can win some benchmarks by using 3x tokens over 3x time, it is a terrible base to build toward the future. Users are no lon…

I really would like to see OpenAI’s focus on efficiency but everytime I use Codex, it wastes tokens like there’s no tomorrow, hitting week limit in a day, where I’m able to use Claude just fine. Maybe it’s based on the codebase, I don’t know, but I have better results with Claude than Codex.

Codex is fabulous at work, where token use is near limitless and ultra-thorough tool use is welcome. Go ahead and fire off searches for look-alike terms on my 96-core cloud instance.

By contrast, Claude Code's bias to make assumptions of reasonableness about underlying systems has proven to be immensely frustrating over the last month or two, both personally and at work. I've wasted days on "that was my mistake. I've been reporting numbers on the old architecture because I hadn't enabled the new one in the config" both at work and home. It's immensely frustrating.

But here we are. Wrestling with energetic idiots in model form, wrangled by over-specific harnesses that struggle to stay off of deranged side-quests.

What a time to be alive!

Re: Claude Code May–August 2026 weekly limits promotion

#247
post #223

Earlier quoted context omitted.

Advanced mesh manipulation, shader writing and editing, 3D math, spatial awareness and analysis. It's not just better, it's the only model that straight up works (sorry for the claude speak). A league of its own. Don't take my word for it, use a simple prompt of "create a shader showing [complex scene]" and see what the other models vomit out, including opus 4.6/4.8/5 and 5.6 sol (compare fable low effort with sol xh…

Vehicle physics/dynamics in my case and yes, same. I got a lot of mileage out of letting it use Opus/Sonnet sub agents for much of the exploratory and implementation work, which cuts down on token use. I got into way fewer "oh, that's nonsense? what about this then?" loops with Fable and it was the first model that actually tried to reason about the full system rather than fixating on details and chasing bits and pie…

No need to switch as they give out free trials and Sol Is available on the 20$ plan. It's very fast for its power. I ask it for insight, read the responses myself, and offer its points back to Claude. More efficient than letting them talk to each other.

Re: Claude Code May–August 2026 weekly limits promotion

#248

Earlier quoted context omitted.

One can, say, hate America and feel its lunch is about to be munched by China and still read: “These labs generated over 16 million exchanges with Claude through approximately 24,000 fraudulent accounts…” and think “oh, there’s alleged evidence of distillation“.

The source is just anthropic saying what they believe and not providing any evidence beyond what they say. No raw chat logs to analyze independently. That's American exceptionalism

It’s not as trustworthy as it could be. Are you using the term as commonly known?

https://en.wikipedia.org/wiki/American_exceptionalism

  Seymour Martin Lipset, a prominent American political scientist and sociologist, argues that the United States is exceptional in that it started from a revolutionary event. He therefore traces the origins of American exceptionalism to the American Revolution, from which the U.S. emerged as "the first new nation" with a distinct ideology, and having a unique mission to transform the world. This ideology, which Lipset calls "Americanism" but is often also referred to as "American exceptionalism", is based on liberty, individualism, republicanism, democracy, meritocracy, and laissez-faire economics; these principles are sometimes collectively referred to as "American exceptionalism".

  As a term in political science, American exceptionalism refers to the United States' status as a global outlier both in good and bad ways. Critics of the concept say that the idea of American exceptionalism suggests that the U.S. is better than other countries, has a superior culture, or has a unique mission to transform the planet and its inhabitants.
Like, when I consider the Tuskegee Syphilis Experiments or MK Ultra, or Flock, I have bad things to say about them but American exceptionalism specifically wouldn’t cross my mind. Corporations anywhere playing a card close to the chest or even lying… superiority, exceptionalism, aren’t my top reference points.

Re: Claude Code May–August 2026 weekly limits promotion

#249
post #198

Anthropic has just announced extending the limits through August 31st with plans to make the new limits permanent. https://xcancel.com/ClaudeDevs/status/2089798442306711646

I was just gonna blast them for the infinite promo extensions and Fable, but at least they apparently have noticed this indecisiveness problem themselves and making it permanent is definitely the best way to solve it, lol!

After they perma-extended Fable into including it into the max plan, I'm willing to give them the benefit of the doubt with this one.

Re: Claude Code May–August 2026 weekly limits promotion

#250
Everyone says that you hit token limits after some time using either Claude Code or its web version. Even though GPT 5.5 is cheaper and doesn't impose token limits, it's just too non-nuanced. The only points for which I still stick to using Claude are these:

- I actually rarely hit the token limits using my $20/mo web plan (switch chats when the current one feels "bloated" due to huge context and therefore the token drain), which even covers some of my coding sessions using Claude Code. - The visuals and "interactive" elements are still not introduced in GPT's web UI, unlike Claude's. - The nail in the coffin is the fact that Opus 4.8/5 is just BETTER at doing my RTL verification review jobs than GPT 5.5.

I am not glazing the model; it's just a personal preference for getting the job done...

Post reply on HN