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

661–670 of 822 posts

Re: Claude Sonnet 5

#661

Post by TurdF3rguson »

TurdF3rguson wrote: post #534
jimbo808 wrote: post #522

Earlier quoted context omitted.

https://www.judiciary.senate.gov/imo/media/doc/2023-07-26_-_... https://xcancel.com/coinbureau/status/2071330294452666695 https://www.techpolicy.press/transcript-senate-hearing-on-pr... > "Once the weights of a model are public, they cannot be retrieved. If a model possesses dangerous capabilities, it is permanently out in the wild... We need to consider regulatory frameworks that account for the unique risks of open…

That's true I guess. If someone decides a model needs more guard rails, anthropic can adjust it, whereas with open weights it's too late. It definitely sounds like the kind of thing that ends the world in B sci-fi thrillers.

Curious if I'm being downvoted by people who think there will never be a model with dangerous capabilities? Or people who think when it happens we shouldn't add guard rails?

Re: Claude Sonnet 5

#662

Post by jurgenburgen »

boc wrote: post #608
throwaway27448 wrote: post #579

Earlier quoted context omitted.

Have you really found claude to much more more capable than eg deepseek? Anthropic has little to no chance of producing a competitive business model in the long term.

> Anthropic has little to no chance of producing a competitive business model in the long term. Extraordinary thing to say about the fastest growing company in the history of capitalism. They will soon have access to public markets, essentially unlimited capital, and can build insanely large models that they don't have to make public... ever. They can just use those models to run their business, train better models,…

> Extraordinary thing to say about the fastest growing company in the history of capitalism. They will soon have access to public markets, essentially unlimited capital

There is no such thing as unlimited capital. The faster they grow the faster they burn capital. Eventually it will run out.

Re: Claude Sonnet 5

#663

Post by jon-wood »

matheusmoreira wrote: post #573
chewz wrote: post #556

Earlier quoted context omitted.

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.

Even with Opus 4.8 I have to try pretty hard to maintain 100% weekly usage. I'm actively trying not to be efficient at this point. Now that the ban is lifted, max effort Fable 5 is gonna solve this problem quite neatly. Fable to plan and review, Sonnet for the implementation. Wait, never mind that. Subscribers will only have Fable for a week.

Why are you optimising for token use rather than getting whatever tasks you're trying to do done? Max effort Opus will happily sit there talking to itself for five minutes fixating on every tiny detail while Sonnet or even Haiku will just blast through the problem and be ready for the next one in seconds.

Re: Claude Sonnet 5

#664

Post by jurgenburgen »

theshrike79 wrote: post #643
Abishek_Muthian wrote: post #571

Earlier quoted context omitted.

I'm a senior skilled developer and I find Anthropic $20 + Open AI $20 + OpenCode Go $10 offers more value than $100 on any particular service. Juggling between all different models/agents is quite simple with Zed. A caution about OpenCode Go though, the entire company seems to be run by AI so there's lot of billing related issues with zero support. I subscribe new every month as I lost money due to double payment wit…

I've been running about the same stack for well over a year now, Anthropic cheapest + OpenAI cheapest + z.ai coder (black friday offer). The Z.AI is a bit wonky, so now I'm moving to Openrouter for Qwen+Kimi+Deepseek?GLM My summer project is to figure out a proper agentic system where a "big" model does the planning, but automatically uses a cheaper one for the grunt work. Having Opus to config edits is just stupid :…

> My summer project is to figure out a proper agentic system where a "big" model does the planning, but automatically uses a cheaper one for the grunt work. Having Opus to config edits is just stupid :)

My company pays for the tokens so I don’t care. Biggest model and max everything. The slight risk of a smaller model making a mistake is more expensive than just running the bigger model all the time.

Re: Claude Sonnet 5

#665

Post by jimbo808 »

socalgal2 wrote: post #657
jimbo808 wrote: post #610

Earlier quoted context omitted.

I think I might have written a comment similar to yours maybe 6 months or a year ago. I'm not quite sure to respond to these sorts of replies. I have used LLMs/Claude Code quite extensively professionally and was a very early adopter, have built tooling around LLM/agentic development, and genuinely embraced it. They aren't useless, but the short term gains you think you're getting come at a very steep price that you…

It’s hard to know if your experience is relevant from 6 months to year ago. The models are getting better every couple of months. My current experience is mostly like the other senior above. For me the last 4 months I’ve gone from mostly writing code by hand to writing almost no code by hand. I guide the LLM and it’s a force multiplier. I review its code and discuss with it how to test and what needs changing and it…

Uh, I didn't say I stopped using LLM's 6mos to a year ago. I have to for my job, it was just that long ago that I began to understand that they aren't what they seem and definitely aren't a "force multiplier," more like a "debt generator."

Re: Claude Sonnet 5

#666

Post by chewz »

Thanemate wrote: post #650
pmarreck wrote: post #557

Earlier quoted context omitted.

> 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…

The skilled seniors better stop downplaying what actually led them to be skilled in the first place, and realize that the conditions to develop that skill has been gone and almost deemed unproductive in today's workplace. Not disagreeing that LLM's are a force multiplier, but I highly doubt whatever value will end up finding multiplying in the next generation of seniors, at this rate. It's surreal to me that I have t…

I have been thinking about it - paid apprenticeship is the answer - just as it is in other professions like medicine.

Seniors should be paid to actively introduce juniors to the trade over couple of years. No more bootcamp entry.

And it would be significant $ for senior to agree to expend his time and energy on software engineering apprentices. There would be also very limited number of places with good seniors. Exactly like medicine for a long time now.

In fact it is already happening in some companies I know about - seniors geting their bonuses tied to juniors being under their wings.

Re: Claude Sonnet 5

#667

Post by seer »

jimbo808 wrote: post #621
aix1 wrote: post #617

Earlier quoted context omitted.

> a very steep price that you may not actually account for Could you elaborate on this steep price that you have in mind? What does it consist of?

Technical debt and skill atrophy Technical debt due to accumulated excessively verbose, badly architected, often redundant, feature-bloated code which always looks good, even upon earnest review, but actually sucks and becomes extremely difficult to maintain in ways which are not obvious in code review. The issue is this: your tooling can help, and can make you feel better, and you might think you wrote all the promp…

Yeah but I think going back to hand writing bespoke code is not coming back, the genie is out of the bottle.

But we could build much better tooling around keeping the agents honest. The problems you are describing are absolutely real and I see them every they.

One friend of mine had almost a mental breakdown when he just went ahead and drilled a bug producing Claude to the point that it itself admitted it was “a piece of shit”. He knew that arguing with an LLM agent is more than useless, but it was cathartic for sure.

When I encounter a situation like this I always go down to - have I done everything I could to catch these errors in my automated validation, and update it as needed.

Agents are also more than happy to spend tokens refactoring, once you have such a test harness be good enough, producing successively better and more general abstractions is quite easy.

The old rule of thumb of “make it work, make it fast, make it pretty” still applies , just with much much faster iteration speed.

It seems with agents people have forgotten the last 2 steps since they produce a _working_ solution, and it might be hard to justify spending time “cleaning it up”, but this still remains essential.

Re: Claude Sonnet 5

#668

Post by marsven_422 »

ricardobayes wrote: post #308
keeda wrote: post #253

Earlier quoted context omitted.

Some napkin math -- total global labor compensation is about 50% of the GDP, which puts it in the USD 50 - 60 Trillion range: https://ourworldindata.org/grapher/labor-share-of-gdp This source claims that knowledge workers alone (probably because they are paid much more) account for 35 - 50 Trillion of that: https://github.com/danielmiessler/Substrate/blob/main/Data/K... If LLMs can boost their productivity even by an…

I am deeply surprised by the silence of philosophers, sociologists, liberal arts majors, economists. Where are the think tanks who contemplate and debate the societal aspects? The tech is advancing full steam but the "other side" doesn't feel anywhere nearly ready.

[dead]

Re: Claude Sonnet 5

#669

Post by grim_io »

adam_arthur wrote: post #319
theLiminator wrote: post #28

Seems like the way to go for any smaller models is to only use the low reasoning levels, and for anything where you'd want it to reason harder, to just use a larger model. In effect, high reasoning only makes sense when you're using the frontier model and need extra performance (higher levels of reasoning are never pareto optimal unless you're at the largest model size).

I've found disabling reasoning entirely but adding a "reason" to the JSON response from the LLM to work significantly faster and consume many fewer tokens for narrowly scoped prompts. At least for Claude family models. e.g. { "reason": " ", "selection": " " } I'm sure native reasoning produces more accurate results, but for my use case the quality was about the same, and the model would reason for thousands of tokens…

What you are doing, is producing an unnecessary summary of the result, not reasoning that models do to come up with the result.

I don't get what value you get out of this.

Re: Claude Sonnet 5

#670

Post by monk_e_boy »

einichi wrote: post #654
Thanemate wrote: post #650

Earlier quoted context omitted.

The skilled seniors better stop downplaying what actually led them to be skilled in the first place, and realize that the conditions to develop that skill has been gone and almost deemed unproductive in today's workplace. Not disagreeing that LLM's are a force multiplier, but I highly doubt whatever value will end up finding multiplying in the next generation of seniors, at this rate. It's surreal to me that I have t…

This is something for educators to deal with, not a 50+ senior IC, but yes your point is extremely important.

As an educator (UK) it's very hard to find people with experience to join us. The pay is SO crap and the workload is huge. Trying to teach complex, large systems is impossible, because we don't have them. We can't throw 1,000 files and 20,000 lines of code at a student and teach them how the system was engineered. We can show them toy systems.... which is fine if there is a work route that takes them and nutures them for 5 or so years. But without that pipeline, shrug not sure what we do about it
Post reply on HN