Brutal. I've been noticing that 4.7 eats my Max Subscription like crazy even when I do my best to juggle tasks (or tell 4.7 to use subagents with) Sonnet 4.6 Medium and Haiku. Would love to know if anybody's found ideal token-saving approaches.
Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
61–70 of 620 posts
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#62[flagged]
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#6345% is brutal if you're building on top of these models as a bootstrapped founder. The unit economics just don't work anymore at that price point for most indie products. What I've been doing is running a dual-model setup — use the cheaper/faster model for the heavy lifting where quality variance doesn't matter much, and only route to the expensive one when the output is customer-facing and quality is non-negotiable.…
> if you're building on top of these models as a bootstrapped founder
This is going to be blunt, but this business model is fundamentally unsustainable and "founders" don't get to complain their prospecting costs went up. These businesses are setting themselves up to get Sherlocked.
The only realistic exit for these kinds of businesses is to score a couple gold nuggets, sell them to the highest bidder, and leave.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#64releases 4.8 and deletes everything else. and now 4.8 costs 500% more than 4.7. i wonder what it would take for people to start using kimi or qwen or other such.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#65Subsidies don't last forever.
Running an open like Kimi constantly for an entire month will cost around 100-200$, being roughly equal to a pro-tier subscription. This is not my estimate so I’m more than open to hearing refutations. Kimi isn’t at all Opus-level intelligent but the models are roughly evenly sized from the guesses I’ve seen. So I don’t think it’s the infra being subsidized as much as it’s the training.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#66We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
The lock in is so incredibly poor. I could switch to whatever provider in minuets.
But it requires that one does not do something stupid.
Eg. For recurring tasks: keep the task specification in the source code and just ask Claude to execute it.
The same with all documentation, etc.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#67Earlier quoted context omitted.
Hey, Boris from the Claude Code team here. People were getting extra cyber warnings when using old versions of Claude Code with Opus 4.7. To fix it, just run claude update to make sure you're on the latest. Under the hood, what was happening is that older models needed reminders, while 4.7 no longer needs it. When we showed these reminders to 4.7 it tended to over-fixate on them. The fix was to stop adding cyber remi…
How do you justify the API and web UI versions of 4.7 refusing to solve NYT Connections puzzles due to "safety"? https://x.com/LechMazur/status/2044945702682309086
To be fair, reading the New York Times is a safety risk for any intelligent life form these days. But still.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#68For now, I'm planning to stick with Opus 4.5 as a driver in VSCode Copilot.
My workflow is to give the agent pretty fine-grained instructions, and I'm always fighting agents that insist on doing too much. Opus 4.5 is the best out of all agents I've tried at following the guidance to do only-what-is-needed-and-no-more.
Opus 4.6 takes longer, overthinks things and changes too much; the high-powered GPTs are similarly flawed. Other models such as Sonnet aren't nearly as good at discerning my intentions from less-than-perfectly-crafted prompts as Opus.
Eventually, I quit experimenting and just started using Opus 4.5 exclusively knowing this would all be different in a few months anyway. Opus cost more, but the value was there.
But now I see that 4.7 is going to replace both 4.5 and 4.6 in VSCode Copilot, and with a 7.5x modifier. Based on the description, this is going to be a price hike for slower performance — and if the 4.5 to 4.6 change is any guide, more overthinking targeted at long-running tasks, rather than fine-grained. For me, that seems like a step backwards.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#69We dropped Claude. It's pretty clear this is a race to the bottom, and we don't want a hard dependency on another multi-billion dollar company just to write software We'll be keeping an eye on open models (of which we already make good use of). I think that's the way forward. Actually it would be great if everybody would put more focus on open models, perhaps we can come up with something like the "linux/postgres/git…
>we don't want a hard dependency on another multi-billion dollar company just to write software One of two main reasons why I'm wary of LLMs. The other is fear of skill atrophy. These two problems compound. Skill atrophy is less bad if the replacement for the previous skill does not depend on a potentially less-than-friendly party.
You can argu that you will have skill atrophy by not using LLMs.
We have gone multi cloud disaster recovery on our infrastructure. Something I would not have done yet, had we not had LLMs.
I am learning at an incredible rate with LLMs.
Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
#70I was using Opus 4.7 just yesterday to help implement best practices on a single page website. After just ~4 prompts I blew past my daily limit. Another ~7 more prompts & I blew past my weekly limit. The entire HTMl/CSS/JS was less than 300 lines of code. I was shocked how fast it exhausted my usage limits.
I haven't used Claude. Because I suspect this sort of things to come.
With enterprise subscription, the bill gets bigger but it's not like VP can easily send a memo to all its staff that a migration is coming.
Individuals may end their subscription, that would appease the DC usage, and turn profits up.