News for hackers. Stuff that matters.
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by paulddraper on Monday July 07, 2025 @03:15PM (#44493708)
I do not use Opus for coding, I much prefer Sonnet.

Many tasks work better with iteration/supervision and Sonnet makes that feasible.

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bhaktatejas922 on Monday July 07, 2025 @04:38PM (#44494447)
yeah same. I feel like Opus tends to be slightly more sycophancy leaning on technical topics
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by helsinki on Tuesday July 08, 2025 @07:51AM (#44499141)
Interesting. I use Opus exclusively (like $1000/day in tokens) via Claude Code. Do you really think Sonnet is better for programming? I’m not sure I agree, though I’d love to save $900/day by taking you up on it.
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by stoken on Tuesday July 08, 2025 @09:32AM (#44499815)
Genuine: how? I assume you're using something like cc-usage to get that value. $1k/day is tons. Would genuinely love to know how you're managing to keep the inference burning through that much a day, as I'd love to do the same, but even with 2-4 simultaneous sessions running fairly continuously, mostly on Opus for 10-12 hours a day, I get maybe $500/day. What's your workflow rig/setup look like to get you to that $1k velocity?
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by helsinki on Wednesday July 09, 2025 @06:27PM (#44515341)
I use Vertex and work at a hedge fund. I just spam Claude Code Opus all day long. There’s not much to it, other than I sit at a chair for 12-16 hours and spam poor (actually, rich) Claude. I don’t use the cc usage too - I just look at my GCP bill :(
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by stoken on Thursday July 10, 2025 @11:32AM (#44522143)
I mean, that'll do it :claps:
Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by paulddraper on Tuesday July 08, 2025 @11:04AM (#44500676)
I think the difference without accounting for performance is noticeable but small.

And after accounting performance is in favor of Sonnet.

Re:Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 ... by bhaktatejas922 on Tuesday July 08, 2025 @01:06PM (#44501914)
Im not sure that it's "better". I still use Opus and it's better at coding but needs more steering to be less of a "Yes you're EXACTLY right" every time i suggest a new solution path. Purely anecdotal though