91–100 of 292 posts
If I'm close to weekly limits on Claude Code with Anthropic Pro, does that go away or stretch out if I switch to Haiku?
I am afraid Claude Pro subscription got 3x less usage
claude --model Haiku-4.5 doesn't work
Earlier quoted context omitted.
"pay for data on VRAM" RAM of GPU
But that doesn't make sense? Why would they keep the cache persistent in the VRAM of the GPU nodes, which are needed for model weights? Shouldn't they be able to swap in/out the kvcache of your prompt when you actually use it?
I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.
I wonder what the next smaller model after Haiku will be called. "Claude Phrase"?
I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.
I'm a user who follows the space but doesn't actually develop or work on these models, so I don't actually know anything, but this seems like standard practice (using the biggest model to finetune smaller models)
Certainly, GPT-4 Turbo was a smaller model than GPT-4, there's not really any other good explanation for why it's so much faster and cheaper.
The explicit reason that OpenAI obfuscates reasoning tokens is to prevent competitors from training their own models on them.
claude --model Haiku-4.5 doesn't work
The main thing holding these Anthropic models back is context size. Yes, quality deteriorates over a large context window, but for some applications, that is fine. My company is using grok4-fast, the Gemini family, and GPT4.1 exclusively at this point for a lot of operations just due to the huge 1m+ context.
Is your company Tier 4? Anthropic has had 1M context size in beta for some time now. https://docs.claude.com/en/docs/build-with-claude/context-wi...
This means 2.5 Flash or Grok 4 fast takes all the low end business for large context needs.
I am really interested in the future of Opus; is it going to be an absolute monster, and continue to be wildly expensive? Or is the leap from 4 -> 4.5 for it going to be more modest.
My impression is that Sonnet and Haiku 4.5 are the same "base models" as Sonnet and Haiku 4, the improvements are from fine tuning on data generated by Opus. I'm a user who follows the space but doesn't actually develop or work on these models, so I don't actually know anything, but this seems like standard practice (using the biggest model to finetune smaller models) Certainly, GPT-4 Turbo was a smaller model than G…
And I would expect Opus 4 to be much the same.
Excited to see how fast Haiku can go!