Top all-time · #8550
she-llac
Personal blog · she-llac.comaiprogramming
she-llac is a personal blog at she-llac.com about ai and programming. Since 2026, 9 different Hacker News readers have linked it 9 times, most often “Suspiciously precise floats, or, how I got Claude's real limits”. No feed was found, so read it on the site itself.
Too few sampled comments (8) to say how often HN recommends it.?
Why HN links it
Analyses Claude subscription usage limits and compares plan costs with API pricing, by reverse-engineering plan usage. HN commenters cite it as the source for those cost and limit figures.
Summarised by Claude from a sample of 8 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Suspiciously precise floats, or, how I got Claude's real limits9 people · 9 mentions · first linked 2026-01-25
What Hacker News says?
Apart from local AI, a serious choice is aggregated API such as new-api [0]. An API provider aggregated thousands of accounts has much better stability than a single account. It's also cheaper than the official API because of how the subscription model works, see e.g. the analysis [1]. [0] https://github.com/QuantumNous/new-api [1] https://she-llac.com/claude-limits
Comment linking /claude-limits
on “Claude Code is locking people out for hours”Submitted Suspiciously precise floats, or, how I got Claude's real limits as a story · 2 points
HN discussionYou’re probably thinking of this article: https://she-llac.com/claude-limits
Comment linking /claude-limits
on “Claude Opus 4.7”Some broad assumptions are being made that plans give you a precise equivalent to API cost. This is not the case with reverse engineering plan usage showing cached input is free [0]. If you re-run the math removing cached input the usage cost is ~5-34% more. Was the token plan budget increase [1] proportional to account for this? Can’t say with certainty. Those paying API costs though the price hike is real. [0] htt…
Comment linking /claude-limits
on “Claude Opus 4.7 costs 20–30% more per session”> calculating the exact discount you get using a subscription could be difficult Why can't you derive this discount from experiments? Example of such research https://she-llac.com/claude-limits
Comment linking /claude-limits
on “Price per 1M tokens is meaningless”The fixed consumption plans are offering several times their worth compared to API pricing with completely free cache reads: https://she-llac.com/claude-limits I look at that and think that they must be losing money hand over fist on something like this, not that this shows what their margins are like. If their margins are like this then I don't see why they'd be raising money and shuffling it around in circles. > I…
Comment linking /claude-limits
on “Who's Afraid of Chinese Models?”If you worry about sending your data off for inference, Fireworks is one of the companies serving open models with solid performance and compliance/zero data retention sorted out. OpenCode supports them and many others. Cursor uses them. They don't have the super-cheap cache reads deal that DeepSeek's own endpoint does, but are still well below Anthropic API rates. (Though importantly, you're not paying API rates!)…
Comment linking /claude-limits
on “DeepSeek V4 Pro beats GPT-5.5 Pro on precision”API pricing for Claude is about an order of magnitude more expensive than subscriptions (numbers: https://she-llac.com/claude-limits ). But it may be worth it with DeepSeek V4 Pro, which is currently on discount.
Comment linking /claude-limits
on “A recent experience with ChatGPT 5.5 Pro”This guy tested it: https://she-llac.com/claude-limits "Suspiciously precise floats, or, how I got Claude's real limits" 19hs ago 25 points https://news.ycombinator.com/item?id=46756742 OTOH, with ChatGPT/Codex limits are less of a problem, in general.
Comment linking /claude-limits
on “Porting 100k lines from TypeScript to Rust using Claude Code in a month”