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

331–340 of 620 posts

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

#331

Post by tehjoker »

deadbabe wrote: post #77
tossandthrow wrote: post #69

Earlier quoted context omitted.

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.

Using LLMs as a learning tool isn’t what causes skill atrophy. It’s using them to solve entire problems without understanding what they’ve done. And not even just understanding, but verifying that they’ve implemented the optimal solution.

It's partly that, but also reading and surface level understanding something vs generating yourself are different skills with different depths. If you're learning a language, you can get good at listening without getting good at speaking for example.

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

#332

Post by root_axis »

post-it wrote: post #122
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.

I was worried about skill atrophy. I recently started a new job, and from day 1 I've been using Claude. 90+% of the code I've written has been with Claude. One of the earlier tickets I was given was to update the documentation for one of our pipelines. I used Claude entirely, starting with having it generate a very long and thorough document, then opening up new contexts and getting it to fact check until it stopped…

I have also found LLMs are a great tool for understanding a new code base, but it's not clear to me what your comment has to do with skill atrophy.

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

#333

Post by falkensmaize »

leonidasv wrote: post #285
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…

>perhaps we can come up with something like the "linux/postgres/git/http/etc" of the LLMs I fear that this may not be feasible in the long term. The open-model free ride is not guaranteed to continue forever; some labs offer them for free for publicity after receiving millions in VC grants now, but that's not a sustainable business model. Models cost millions/billions in infrastructure to train. It's not like open-so…

"get obsolete in months"

If you mean obsolete in the sense of "no longer fit for purpose" I don't think that's true. They may become obsolete in terms of "can't do hottest new thing" but that's true of pretty much any technology. A capable local model that can do X will always be able to do X, it just may not be able to do Y. But if X is good enough to solve your problem, why is a newer better model needed?

I think if we were able to achieve ~Opus 4.6 level quality in a local model that would probably be "good enough" for a vast number of tasks. I think it's debatable whether newer models are always better - 4.7 seems to be somewhat of a regression for example.

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

#334

Post by root_axis »

groundzeros2015 wrote: post #330
drivebyhooting wrote: post #224

Earlier quoted context omitted.

I like programming, but I don’t like the job.

Then why are you letting Claude do the fun part?

Obviously, the fun part is delivering value for the shareholders.

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

#335

Post by IgorPartola »

ahartmetz wrote: post #54
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…

>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.

Yeah I am worried about skill atrophy too. Everyone uses a compiler these days instead of writing assembly. Like who the heck is going to do all the work when people forget how to use the low level tools and a compiler has a bug or something?

And don’t get me started on memory management. Nobody even knows how to use malloc(), let alone brk()/mmap(). Everything is relying on automatic memory management.

I mean when was the last time you actually used your magnetized needle? I know I am pretty rusty with mine.

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

#336

Post by dlopes7 »

idopmstuff wrote: post #228
estetlinus wrote: post #169

Earlier quoted context omitted.

Yeah, +1. I will never be working on unsolved problems anyhow. Skill atrophy is not happening if you stay curious and responsible.

Some people talk like skill atrophy is inevitable when you use LLMs, which strikes me as pretty absurd given that you are talking about a tool that will answer an infinite number of questions with infinite patience. I usually learn way more by having Claude do a task and then quizzing it about what it did than by figuring out how to do it myself. When I have to figure out how to do the thing, it takes much more time,…

Asking infinite questions about something does not make you good at “doing” that thing, you get pretty good at asking questions

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

#337

Post by trueno »

_blk wrote: post #164
hgoel wrote: post #74

The bump from 4.6 to 4.7 is not very noticeable to me in improved capabilities so far, but the faster consumption of limits is very noticeable. I hit my 5 hour limit within 2 hours yesterday, initially I was trying the batched mode for a refactor but cancelled after seeing it take 30% of the limit within 5 minutes. Had to cancel and try a serial approach, consumed less (took ~50 minutes, xhigh effort, ~60% of the rem…

From what I understand you shouldn't wait more than 5min between prompts without compacting or clearing or you'll pay for reinitializing the cache. With compaction you still pay but it's less input tokens. (Is compaction itself free?)

is it 5 mins between constant prompting/work or 5 mins as in if i step away from the comp for 5 mins and comp back and prompt again im not subject to reinit?

if it's the latter that's crazy. i dont even know what to do there, compactions already feel like a memory wipe

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

#338

Post by 100ms »

amelius wrote: post #24
ausbah wrote: post #16

is it really unthinkable that another oss/local model will be released by deepseek, alibaba, or even meta that once again give these companies a run for their money

I'm betting on a company like Taalas making a model that is perhaps less capable but 100x as fast, where you could have dozens of agents looking at your problem from all different angles simultaneously, and so still have better results and faster.

I'm excited for Taalas, but the worry with that suggestion is that it would blow out energy per net unit of work, which kills a lot of Taalas' buzz. Still, it's inevitable if you make something an order of magnitude faster, folk will just come along and feed it an order of magnitude more work. I hope the middleground with Taalas is a cottage industry of LLM hosts with a small-mid sized budget hosting last gen models for quite cheap. Although if they're packed to max utilisation with all the new workloads they enable, latency might not be much better than what we already have today

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

#339

Post by dgellow »

tossandthrow wrote: post #264
dgellow wrote: post #156

Earlier quoted context omitted.

Unnecessary nitpicking

Why? One shoting has a very specific meaning, and agentic workflows are not it? What is the implied meaning I should understand from them using one shot? They might refer to the lack of humans in the loop.

You give a prompt, you get a PR. If it is ready to merge with the first attempt, that’s a one shot. The agentic loop is a detail in their context

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

#340

Post by otabdeveloper4 »

IgorPartola wrote: post #335
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.

Yeah I am worried about skill atrophy too. Everyone uses a compiler these days instead of writing assembly. Like who the heck is going to do all the work when people forget how to use the low level tools and a compiler has a bug or something? And don’t get me started on memory management. Nobody even knows how to use malloc(), let alone brk()/mmap(). Everything is relying on automatic memory management. I mean when w…

> an LLM is exactly like a compiler if a compiler was a black box hosted in a proprietary cloud and metered per symbol

Yeah, exactly.

Post reply on HN