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

Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

tokens.billchambers.me

Post reply on HN
Print view View original

171–180 of 620 posts

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#171

Post by monkpit »

ljm wrote: post #118
ahartmetz wrote: post #54

Earlier quoted context omitted.

>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.

Not so much atrophy as apathy. I've worked with people who will look at code they don't understand, say "llm says this", and express zero intention of learning something. Might even push back. Be proud of their ignorance. It's like, why even review that PR in the first place if you don't even know what you're working with?

If I wanted to know what the LLM says, I would have asked it myself, thanks…

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#172

Post by esafak »

aliljet wrote: post #114
dakiol wrote: post #46

We 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…

What open models are truly competing with both Claude Code and Opus 4.7 (xhigh) at this stage?

GLM 5.1 competes with Sonnet. I'm not confident about Opus, though they claim it matches that too.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#173

Post by httgbgg »

manmal wrote: post #85
dktp wrote: post #38

Earlier quoted context omitted.

The idea is that smarter models might use fewer turns to accomplish the same task - reducing the overall token usage Though, from my limited testing, the new model is far more token hungry overall

Well you‘ll need the same prompt for input tokens?

Only the first one. Ideally now there is no second prompt.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#174

Post by xixixao »

dgellow wrote: post #153
dakiol wrote: post #46

We 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…

Another aspect I haven’t seen discussed too much is that if your competitor is 10x more productive with AI, and to stay relevant you also use AI and become 10x more productive. Does the business actually grow enough to justify the extra expense? Or are you pretty much in the same state as you were without AI, but you are both paying an AI tax to stay relevant?

This is the “ad tax” reasoning, but ultimately I think the answer is greater efficiency. So there is a real value, even if all competitors use the tools.

It’s like saying clothing manufacturers are paying the “loom tax” tax when they could have been weaving by hand…

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#176

Post by _blk »

pitched wrote: post #117
jherdman wrote: post #102

Earlier quoted context omitted.

Is this sort of setup tenable on a consumer MBP or similar?

For a 30B model, you want at least 20GB of VRAM and a 24GB MBP can’t quite allocate that much of it to VRAM. So you’d want at least a 32GB MBP.

Is there any model that practically compares to Sonnet 4.6 in code and vision and runs on home-grade (12G-24G) cards?

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#177

Post by gbro3n »

Someone1234 wrote: post #155
aliljet wrote: post #114

Earlier quoted context omitted.

What open models are truly competing with both Claude Code and Opus 4.7 (xhigh) at this stage?

That's a lame attitude. There are local models that are last year's SOTA, but that's not good enough because this year's SOTA is even better yet still... I've said it before and I'll say it again, local models are "there" in terms of true productive usage for complex coding tasks. Like, for real, there. The issue right now is that buying the compute to run the top end local models is absurdly unaffordable. Both in ge…

I completely see your point, but when my / developer time is worth what it is compared to the cost of a frontier model subscription, I'm wary of choosing anything but the best model I can. I would love to be able to say I have X technique for compensating for the model shortfall, but my experience so far has been that bigger, later models out perform older, smaller ones. I genuinely hope this changes through. I understand the investment that it has taken to get us to this point, but intelligence doesn't seem like it's something that should be gated.

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#178

Post by parinporecha »

aliljet wrote: post #114
dakiol wrote: post #46

We 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…

What open models are truly competing with both Claude Code and Opus 4.7 (xhigh) at this stage?

I've had a good experience with GLM-5.1. Sure it doesn't match xhigh but comes close to 4.6 at 1/3rd the cost

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#179

Post by senordevnyc »

alphabettsy wrote: post #167

I’m trying to understand how this is useful information on its own? Maybe I missed it, but it doesn’t tell you if it’s more successful for less overall cost? I can easily make Sonnet 4.6 cost way more than any Opus model because while it’s cheaper per prompt it might take 10x more rounds (or never) solve a problem.

Everything in AI moves super quickly, including the hivemind. Anthropic was the darling a few weeks ago after the confrontation with the DoD, but now we hate them because they raised their prices a little. Join us!

Re: Anonymous request-token comparisons from Opus 4.6 and Opus 4.7

#180

Post by redanddead »

ljm wrote: post #118
ahartmetz wrote: post #54

Earlier quoted context omitted.

>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.

Not so much atrophy as apathy. I've worked with people who will look at code they don't understand, say "llm says this", and express zero intention of learning something. Might even push back. Be proud of their ignorance. It's like, why even review that PR in the first place if you don't even know what you're working with?

What is it in the broader culture that's causing this?
Post reply on HN