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

Claude Sonnet 5

anthropic.com

Post reply on HN
Print view View original

551–560 of 822 posts

Re: Claude Sonnet 5

#551

Post by anonzzzies »

andyroid wrote: post #549
anonzzzies wrote: post #537

Earlier quoted context omitted.

Sure about Dario (and all billionaire) weirdness, but no gains if you are a skilled senior is well, very far out in our experience (our company is 30 years old with mostly the original employees and founders): what we deliver now at the speed and quality we deliver it would have been impossible 10 years ago with our team size of skilled seniors. We replaced all the commercial products our clients and ourselves used w…

> We replaced all the commercial products our clients and ourselves used with our own You’ll never guess what product your clients are looking to replace with their own next.

Sure, that is why you need to be early. I fully believe my company won't make it another 30 years (or 10), so we prepare for that. Also, I will be dead by then, but that is unrelated.

For now everyone is still sufficiently crap at using AI to need help. We had enough clients trying to build something themselves and then come crying to us.

Re: Claude Sonnet 5

#552

Post by entropicdrifter »

jquery wrote: post #530
Robdel12 wrote: post #526

Earlier quoted context omitted.

Dario’s own mouth https://x.com/coinbureau/status/2071330294452666695/mediavie...

Yeesh. “What shall we do sire, when the peasants learn to read?” vibes

You mean to tell me that anyone can own a nail-gun? We can't have people buying their own nail-guns, next thing you know they might build things that aren't up to code!

Re: Claude Sonnet 5

#553

Post by hughw »

andyroid wrote: post #549
anonzzzies wrote: post #537

Earlier quoted context omitted.

Sure about Dario (and all billionaire) weirdness, but no gains if you are a skilled senior is well, very far out in our experience (our company is 30 years old with mostly the original employees and founders): what we deliver now at the speed and quality we deliver it would have been impossible 10 years ago with our team size of skilled seniors. We replaced all the commercial products our clients and ourselves used w…

> We replaced all the commercial products our clients and ourselves used with our own You’ll never guess what product your clients are looking to replace with their own next.

Sure but in the intervening 2 years there's money to be made.

Re: Claude Sonnet 5

#554

Post by whatshisface »

nl wrote: post #477
sanderjd wrote: post #195

Earlier quoted context omitted.

What I want is a harness that knows how to optimize this kind of thing for me.

In practice I don't think any harness (happy to be corrected here!) uses the lesser capability models for writing code. The cost trade-offs are rarely worth it. They are often used for reading code though. To expand on this, while the "big model to write a plan, small model to write the specific code" idea is quite common it trips up on edge cases. In theory the flow works like this: - small fast models read lots of…

> In practice I don't think any harness (happy to be corrected here!) uses the lesser capability models for writing code. The cost trade-offs are rarely worth it.

That's not something I understand very well. The less expensive models will quite happily chug away at tasks, if the codebase is well-structured (small files help a lot) and your instructions are clear. In contrast, I've never seen a large model turn bad instructions (instructions that would cause a human to think before starting) into a result I liked. You can run small models almost 10-100x as long for the same price in dollars, which covers a lot of correction and adjustment.

Why does everyone say the trade-offs are rarely worth it?

Re: Claude Sonnet 5

#555

Post by usef- »

riverbirch wrote: post #439
kolinko wrote: post #382

Earlier quoted context omitted.

From my benchmarks, sadly, it doesn't seem to be the case much. Surprisingly. I found Sonnet comparable in speed to Opus (sic), but perhaps I was testing it wrong?

I can confirm this, I too I'm not seeing much of a difference in practice

Given the chip shortage, I wonder if they push Sonnet to the older chips. It presumably requires less memory.

Re: Claude Sonnet 5

#556

Post by chewz »

matheusmoreira wrote: post #437
AquinasCoder wrote: post #138

Earlier quoted context omitted.

While I appreciate, they publish this information, it's increasingly hard to keep track of it all. I've lost the mental model of how different models at different effort levels perform and what tasks they are good at. In practice, I tend to just use the default on Claude Code that works well enough. But I wonder to what degree other users really play around with these settings to optimize for their project.

I always use Opus 4.8 at max effort for everything. The $20 subscription didn't have enough tokens, but the $100 one had too many of them. So now I just max out Opus in order to maintain 100% weekly utilization.

This is actually very counterproductive with Opus 4.8 - you are wasting a lot of time.

For Opus 4.8 training with overblown internal dialogue and second opinions - Max effort burns just tokens and wastes time without much value. Spinning wheels.

Re: Claude Sonnet 5

#557

Post by pmarreck »

jimbo808 wrote: post #514
doctoboggan wrote: post #29

The cost per task chart is telling me that I should _never_ use Sonnet 5 above medium effort level - Opus always performs better for a given cost. So I guess the takeaway is that if Sonnet 5 medium isn't good enough for you, switch models, not effort levels.

They're actively trying to use lobbying power to make open weight models illegal. So I'm just not going to use their services at all anymore. I don't think they're a net gain if you're a skilled senior, and the hidden cost in terms of technical debt and skill atrophy is just being swept under the rug. I'll be okay without their bullshit generator.

> I don't think they're a net gain if you're a skilled senior

I'm a skilled senior (I'm 54 and been coding since I was about 8; I've been 100% AI-generated code for at least 6 months now and have produced a combination of speed and quality that has astonished me; my velocity is apparent at https://github.com/pmarreck/) and this has been a massive net gain, so your claim is now officially in sheer defiance of reality.

In a skilled senior's hands, this is like an expert power tool. In the hands of someone less-skilled, it is likely also... less-skilled. It's a magnifier.

> and the hidden cost in terms of technical debt and skill atrophy is just being swept under the rug.

Nope, no it's not. It's being reviewed, measured, and controlled against. Because... you WILL need more controls to take full advantage. Look, I even invented a whole new control methodology around it called MFIC: https://gist.github.com/pmarreck/b30aa3ca69cb70a5526f8a63ab8...

Re: Claude Sonnet 5

#558

Post by henryl »

0xbadcafebee wrote: post #250
anthonypasq wrote: post #111

Earlier quoted context omitted.

needs to be on bedrock for me to use it at work

Gemma 4, Kimi K2.5, MiniMax M2.5, gpt-oss, GLM 5, Qwen3 Coder Next, DeepSeek V3.2, Devstral 2, are all available on AWS Bedrock and all are about Haiku level

yes but no caching.

Re: Claude Sonnet 5

#559

Post by pmarreck »

Robdel12 wrote: post #526
andsoitis wrote: post #520

Earlier quoted context omitted.

> They're actively trying to use lobbying power to make open weight models illegal. What is your evidence?

Dario’s own mouth https://x.com/coinbureau/status/2071330294452666695/mediavie...

This does not load (or no longer loads) over here.

Re: Claude Sonnet 5

#560

Post by usef- »

sanderjd wrote: post #362
cunningfatalist wrote: post #244

Earlier quoted context omitted.

You might want to check out Amp: https://ampcode.com/

I appreciate the suggestion! But it isn't clear to me, from reading their marketing site, what they bring to the table from this perspective. Can you give me a more targeted pitch?

This page buried in their docs is a bit better than the homepage imo: https://ampcode.com/manual#why-amp

I haven't used them in a while so my info may be out of date, but they tended to track whatever models were the best and auto-use them for each task (eg, one for planning, subagent for a code search, other frontier for implementing). Their CLI seemed very well thought out to make you do things "the correct way" -- for instance, `/handoff` instead of `/clear`.

Post reply on HN