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

521–530 of 620 posts

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

#521

Post by scrollop »

sutterd wrote: post #473
matheusmoreira wrote: post #419

Earlier quoted context omitted.

The most frustrating part is the quality loss caused by the forced adaptive thinking. It eats 5-10% of my Max 5x usage and churns for ten minutes, only to come back with totally untrustworthy results. It lazily hand-waves issues away in order to avoid reading my actual code and doing real reasoning work on it. Opus simply cannot be trusted if adaptive thinking is enabled.

You don't have to use adaptive thinking. It had been turned off on my main work computer. I was using a different computer on a trip and I started getting so angry at Claude for doing a bad job. I evetually figured out it was adaptive thinking and set it to "hard" and it started working again. At the time I think "hard" was the top choice. With 4.7, my computer now shows "xhard", which I assume is the equivelent sett…

"With Opus 4.6, extended thinking was a toggle you managed: turn it on for hard stuff, off for quick stuff. If you left it on, every question paid the thinking tax whether it needed to or not. Now, with Opus 4.7, extended thinking becomes adaptive thinking. "

https://claude.com/resources/tutorials/working-with-claude-o...

You want extended thinking? It's not adaptive thinking and opus will turn it on if it thinks it needs to. But it probably won't, according to user reports as tokens are expensive. Except opus 4.7 now uses 35% more and outputs more thinking tokens.

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

#522

Post by ozgrakkurt »

xpe wrote: post #480
Bridged7756 wrote: post #233

Earlier quoted context omitted.

Mirrors my sentiment. Those tools seem mostly useful for a Google alternative, scaffolding tedious things, code reviewing, and acting as a fancy search. It seems that they got a grip on the "coding LLM" market and now they're starting to seek actual profit. I predict we'll keep seeing 40%+ more expensive models for a marginal performance gain from now on.

> Those tools seem mostly useful for a Google alternative, scaffolding tedious things, code reviewing, and acting as a fancy search. Just to get a sense for the rate of change, imagine if you took a survey. Compare what people said about AI tools... 3 years ago, 2 years ago, 1 year ago, 6 months ago. Then think about what is plausible that people will be saying in 3 months, 6 months, 9 months ... Moving the goalposts…

Can you explain this literature review process?

I don't believe you can do a same quality job with an LLM in 5 minutes.

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

#523

Post by Jarred »

equasar wrote: post #409
blahblaher wrote: post #56

Earlier quoted context omitted.

qwen3.5/3.6 (30B) works well,locally, with opencode

The thing I dislike about OpenCode is the lack of capabilities of their editor, also, resource intensive, for some reason on a VM it chuckles each 30 mins, that I need to discard all sessions, commits, etc. I don't know if it is bun related, but in task manager, is the thing that is almost at the top always on CPU usage, turns out for me, bun is not production ready at all. Wish Zed editor had something like BigPickl…

> turns out for me, bun is not production ready

What issue did you run into?

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

#524

Post by vanviegen »

mrandish wrote: post #455
codethief wrote: post #430

Earlier quoted context omitted.

> > Why are you handwaving things away though? I've got you on max effort. I even patched the system prompts to reduce this. In my experience, prompts like this one, which 1) ask for a reason behind an answer (when the model won't actually be able to provide one), 2) are somewhat standoff-ish, don't work well at all. You'll just have the model go the other way. What works much better is to tell the model to take a st…

> when the model won't actually be able to provide one This is key. In my experience, asking an LLM why it did something is usually pointless. In a subsequent round, it generally can't meaningfully introspect on its prior internal state, so it's just referring to the session transcript and extrapolating a plausible sounding answer based on its training data of how LLMs typically work. That doesn't necessarily mean th…

> In a subsequent round, it generally can't meaningfully introspect on its prior internal state

It can't do any better in the moment it's making the choices. Introspection mostly amounts to back-rationalisation, just like in humans. Though for humans, doing so may help learning to make better future decisions in similar situations.

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

#526

Post by tobyhinloopen »

axpy906 wrote: post #402
rectang wrote: post #68

For 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 f…

Why not just use Sonnet?

Sonnet is very clearly worse than Opus for a lot of tasks. Sonnet is still awesome, but less so.

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

#528

Post by vanviegen »

krackers wrote: post #407
_blk wrote: post #164

Earlier quoted context omitted.

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?)

>pay for reinitializing the cache Why can't they save the kv cache to disk then later reload it to memory?

Isn't that how the kv cache currently works? Of course they could decide to hold on to cache items for longer than an hour, but the storage requirements are pretty significant while the chance of sessions resumption slinks rapidly.

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

#529

Post by gbro3n »

lelanthran wrote: post #422
gbro3n wrote: post #344

Earlier quoted context omitted.

Do you think if you or me stopped using AI that everyone else will too? We're still what we always were - problem solvers who have gained the ability to learn and understand systems better that the general population, communicate clearly (to humans and now AIs). Unfortunately our knowledge of language APIs and syntax has diminished in value, but we have so many more skills that will be just as valuable as ever. As th…

> Unfortunately our knowledge of language APIs and syntax has diminished in value, but we have so many more skills that will be just as valuable as ever. There were always jobs that required those "many more skills" but didn't require any programming skills. We call those people Business Analysts and you could have been doing it for decades now. You didn't, because those jobs paid half what a decent/average programme…

I guess we will need to wait and see if AI can remove ALL of the complexity that requires a software engineer over a business analyst. I can't currently believe that it will. BA's I've worked with vary in technical capability from 'having coded before and understanding DB schema basics and network architecture' to 'I know how the business works but nothing about computers'. If we got to the point in the future where every computer system ran on the same frameworks in the same way, and AI understood it perfectly, then maybe. But while AI is a probabilistic technology manipulating deterministic systems, we will always need people to understand whats going on, and whether they write a lot of code or not, they will be engineers, not analysts. Whether it's more or less of those people, we will see.

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

#530

Post by bobkb »

matheusmoreira wrote: post #431
codethief wrote: post #430

Earlier quoted context omitted.

> > Why are you handwaving things away though? I've got you on max effort. I even patched the system prompts to reduce this. In my experience, prompts like this one, which 1) ask for a reason behind an answer (when the model won't actually be able to provide one), 2) are somewhat standoff-ish, don't work well at all. You'll just have the model go the other way. What works much better is to tell the model to take a st…

That's good advice. I managed to get the session back on track by doing that a few turns later. I started making it very explicit that I wanted it to really think things through. It kept asking me for permission to do things, I had to explicitly prompt it to trace through and resolve every single edge case it ran into, but it seems to be doing better now. It's running a lot of adversarial tests right now and the resu…

> Opus 4.6 DISABLE_ADAPTIVE_THINKING=1

Strangely this option was not working for many of us on a team plan

Post reply on HN