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

Claude Code May–August 2026 weekly limits promotion

support.claude.com

Post reply on HN
Print view View original

181–190 of 275 posts

Re: Claude Code May–August 2026 weekly limits promotion

#181

Post by alightsoul »

jimbob45 wrote: post #176
alightsoul wrote: post #145

Earlier quoted context omitted.

They are not paying billions anymore. They just switched to buying and then destroying books. Arguably that's worse than training off of Anna's archive which Chinese companies still do. This comment is another example of American exceptionalism.

Can you really hold them responsible for book burning when they’re being compelled to do so by governmental laws? Seems like you should be pointing your finger at lawmakers, if anywhere.

Me? A lowly commoner without hundreds of millions to lobby them? Why aren't American ai companies doing so? Too busy training models? They're shooting themselves in the foot when they could just use Anna's archive and lobbying is cheaper than paying billions in copyright settlements. Oh wait I am wrong. Shredding and scanning books is much cheaper than lobbying to use Anna's archive. Still can't do anything because I don't have money for lobbying

Re: Claude Code May–August 2026 weekly limits promotion

#182

Post by oh_no »

20k wrote: post #40
swader999 wrote: post #9

Looking like this will be the last month with Anthropic. Between the outages and just overall crap utility of Opus/Fable lately...

They'll all be getting around to this sooner or later, its just too expensive

yes and no, anthropic and openai are losing money on people who max out their sub, but openai has a lot more room to play with with much cheaper models to serve (by all signs we have from actual api/task pricing)

Re: Claude Code May–August 2026 weekly limits promotion

#183

Post by raincole »

sethops1 wrote: post #144
jryle70 wrote: post #118

Earlier quoted context omitted.

Their revenue has increased dramatically. The run rate was 9B in Dec, 19B in Mar, 47B in May. It's now at 65B. https://www.bloomberg.com/news/articles/2026-08-17/anthropic...

Annualized. Which is another word for made-up.

If you don't understand a concept, perhaps restrain yourself from commenting on it.

Re: Claude Code May–August 2026 weekly limits promotion

#184

Post by wccrawford »

throwup238 wrote: post #117
bicepjai wrote: post #101

Earlier quoted context omitted.

I had the opposite experience. Claude models and its harness feel like they are set to eat tokens for everything, especially if it’s ultracode effort. I have seen it spawn 6 agents and eat my 4-hour quota right in front of me. Codex is on point and follows instructions well even with max effort. I like my analogy of Claude being garrulous and Codex being laconic. If I see more limit hits in same sitting session, I ha…

Just before I canceled my 20x Max sub I had a day where I had ~15% of my weekly I was trying to burn. I set it on ultracode and because I had set the max agents 32 for another project and forgot, the five research agents ended up spinning up a total of 26 subagents and burned through the remainder of my weekly in the span of 20 minutes before I noticed and shut it down. “No, not like THAT!”

Claude did the same thing to me the other day. I ran out of my 5 hr limit, and it went into my $100 credit they had given me. Multiple parallel agents. It ate it in no time flat.

When I checked, all that credit was gone, I still wasn't into the next 5 hours, and all the agents had failed, returning nothing.

I didn't even get anything for burning all that credit. If I had paid for it, I'd be very, very pissed.

Re: Claude Code May–August 2026 weekly limits promotion

#185

Post by numandina »

dgabriel wrote: post #102
numandina wrote: post #90

Earlier quoted context omitted.

It's blowing my mind. Fable is the only AI model I use for coding, everything else is garbage for my use case.

I'm curious about your specific use case, if you're comfortable sharing it here.

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 xhigh).

Re: Claude Code May–August 2026 weekly limits promotion

#187

Post by numandina »

viccis wrote: post #113
numandina wrote: post #90

Earlier quoted context omitted.

It's blowing my mind. Fable is the only AI model I use for coding, everything else is garbage for my use case.

Tbh the extreme discrepancies between very confidently made statements about "X is better than Y" a sign a to me this is something where peoples' biases are out of control. Not saying you are wrong. Just that these things are so hard to evaluated apples to apples and that things like under-the-hood routing changes muddy the waters so much that it's really hard to get reasonable assessments.

My tests are very visual based and easy to notice when the seed/temp or the routing or the A/B test comes into play. And it's been months of working with these models so comparison is straightforward and robust. Fable is the first time I can use AI to code with good results while everyone has been doing it for ages before me.

Re: Claude Code May–August 2026 weekly limits promotion

#188

Post by halfmatthalfcat »

stanmancan wrote: post #173
WhiteDawn wrote: post #124

Earlier quoted context omitted.

Not to sound like a mark, I try to not get attached to any of these providers. I've jumped between copilot, claude, gemini and chatgpt since the start of the year. chatgpt wasn't even worth looking at early this year. Anthropic has the smarter models for sure, and seems to be default in corporate. However, the amount of budget you get with GPT as a user is much better, the harness feels more polished, and the models…

> and it's likely producing better output to keep a human in the loop rather than trying to solve the world independently and making multiple incorrect assumptions. I was just discussing this with a co-worker yesterday. I would really like a model (or harness?) that worked with me instead of for me. Walk me through its choices and decisions, let me correct it and guide it along. I would be way more confident in it's…

Those exist and they're called orchestration skill frameworks like Superpowers, GetShitDone, etc.

Re: Claude Code May–August 2026 weekly limits promotion

#189

Post by wccrawford »

andyjohnson0 wrote: post #168

The whole thing seems pretty opaque. I have a personal Pro subscription that I'm using exclusively with Claude Code on personal projects. I have no idea how close I'm currently getting to any limits, or whether that will start happening tomorrow. Nothing I've been able to find has really clarified it either way.

I've been using it on a few personal projects and run into the limits quite often. With Sonnet on high, I often hit right about the 5 hr mark when it resets. With Opus, I'll hit sooner.

I'm kind of surprised that you haven't been watching it with /usage to see where you're at. I've had a couple times that it ran out and lost what it was doing and had to start over, so I've gotten more careful.

And the time it burned $100 credit (that they gave us) and the fizzled with multiple agents, leaving me nothing of that work... Well, that was certainly instructive.

Post reply on HN