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

591–600 of 620 posts

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

#591

Post by estetlinus »

lobf wrote: post #311
stringfood wrote: post #218

Earlier quoted context omitted.

I have never learned so quickly in my entire life than to post a forum thread in its entirety into a extended think LLM and then be allowed to ask free form questions for 2 hours straight if I want to. Having my questions answered NOW is so important for me to learn. Back in the day by the time I found the answer online I forgot the question

Same. I work in the film industry, but I’ve always been interested in computers and have enjoyed tinkering with them since I was about 5. However, coding has always been this insurmountably complicated thing- every time I make an effort to learn, I’m confronted with concepts that are difficult for me to understand and process. I’ve been 90% vibe coding for a year or so now, and I’ve learned so much about networking j…

I pivoted from the film industry into AI 10 years ago. My end game is to replace movie magic.

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

#592

Post by matheusmoreira »

bobkb wrote: post #531
matheusmoreira wrote: post #423

Earlier quoted context omitted.

I don't think there's a bias here. I'd say my task is of somewhat high complexity. I'm using Claude to assist me in implementing exceptions in my programming language. It's a SICP chapter 5.4 level task. There are quite a few moving parts in this thing. Opus 4.6 once went around in circles for half an hour trying to trace my interpreter's evaluator. As a human, it's not an easy task for me to do either. I think the p…

‘effort high/max’ seems to be working though

The problem I described occurred on Claude Code, Opus 4.7/1M, max effort, patched system prompts with all "don't think for simple stuff" instructions removed as well as CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1 even though Opus 4.7 ignores it.

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

#593

Post by matheusmoreira »

virtualritz wrote: post #548
matheusmoreira wrote: post #389

Earlier quoted context omitted.

It thinks less and produces less output tokens because it has forced adaptive thinking that even API users can't disable. Same adaptive thinking that was causing quality issues in Opus 4.6 not even two weeks ago. The one bcherny recommended that people disable because it'd sometimes allocate zero thinking tokens to the model. https://news.ycombinator.com/item?id=47668520 People are already complaining about low quali…

So CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING=1 is not available/is ignored in 4.7?

It is ignored by Opus 4.7.

https://code.claude.com/docs/en/model-config

> Opus 4.7 always uses adaptive reasoning. The fixed thinking budget mode and CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING do not apply to it.

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

#594

Post by matheusmoreira »

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…

> You don't have to use adaptive thinking.

With Opus 4.7 you absolutely do. Users don't have a choice.

https://code.claude.com/docs/en/model-config

> Opus 4.7 always uses adaptive reasoning. The fixed thinking budget mode and CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING do not apply to it.

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

#595

Post by matheusmoreira »

andersa wrote: post #413
bashtoni wrote: post #412

Earlier quoted context omitted.

Only if you set `ENABLE_PROMPT_CACHING_1H`, which was mentioned in the release notes for a recent Claude Code release but doesn't seem to be in the official docs.

Bruh. It's getting hard to track down all these MAKE_IT_ACTUALLY_WORK settings that default to off for no reason.

For me it's gotten to the point where I have a wrapper script that applies like 5 environment variables and even patches the system prompt strings prior to every Claude Code invocation.

After the Claude Code source code leak someone discovered that some variables are read directly from the process environment. Can't even trust that setting them in ~/.claude/settings.json will work!

I've actually started asking Claude itself to dissect every Claude Code update in order figure out if it broke some part of the Rube Goldberg machine I was forced to set up.

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

#596

Post by matheusmoreira »

xvector wrote: post #577
scrollop wrote: post #520

Earlier quoted context omitted.

Not when you want extended thinking - you select extended thinking and opus decides if you get it with apativenthinking. "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/…

...are you talking about the app? Come on. The app is for quick queries. You should be using Claude Code or Cowork.

I've gotten quite a bit of work done on claude.ai and the mobile app though. It's been good for code review. The GitHub connector is a bit clunky but it works.

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

#597

Post by viccis »

margalabargala wrote: post #464
viccis wrote: post #396

Earlier quoted context omitted.

I would argue that if you've just watched videos about building computers and haven't sat down and done one yourself, then yeah I don't see any evidence that you've learned how to build a computer.

And, so the anti-LLM argument goes, if you've not built the computer you can't learn anything about what computers could be used for.

That's not the anti-LLM argument, that's a brand new argument you made up.

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

#598

Post by viccis »

post-it wrote: post #454
viccis wrote: post #392

Earlier quoted context omitted.

It's good that it's working for you but I'm not sure what this has to do with skill atrophy. It sounds like you never had this skill (in this case, working with that particular system) to begin with. >I have a significantly better understanding of the codebase than I would without AI at this point in my onboarding One of the pitfalls of using AI to learn is the same as I'd see students doing pre-AI with tutoring serv…

> If you were on a plane flight with no wifi, and you wanted to do some dev work locally on your laptop, how comfortable would you be vs if you had done all that work yourself rather than via Claude? Probably about as comfortable as I would be if I also didn't have my laptop and instead had to sketch out the codebase in a notebook. There's no sense preparing for a scenario where AI isn't available - local models are…

So then the argument isn't so much that skill decay isn't an issue but rather that the skill is inherently worthless moving forward. I'm not sure I agree, but I also got a compsci education because I have loved doing it since childhood rather than because I just wanted to make money, and I can see how the latter group would vehemently disagree with me.

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

#599

Post by natdempk »

wallst07 wrote: post #551
mrandish wrote: post #455

Earlier quoted context omitted.

> 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…

It's worked for me when I ask why with a stated goal of preventing the same error the next time. "Why did you guess at the functions signature and get it wrong, what information were you using and how can we prevent it next time." Is that not the right approach?

This can work, but it's sort of not the same as providing actual reasoning behind "why did you do/say X?" -- this is basically asking them model to read the conversation, from the conversation try to understand "why" something happened, and add information to prevent it from being wrong next time. That "why" something went wrong is not really the same as "why" the model output something.

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

#600

Post by xpe »

ozgrakkurt wrote: post #555
xpe wrote: post #537

Earlier quoted context omitted.

I don't mean writing a literature review. I mean reviewing the literature to find what I need. My point is that this was not practical with "fancy search" three years ago by which I mean Google-like search engines. My example: I wanted to get a sense for the feasibility of doing a project that blends Gaussian Processes, active learning, and pairwise comparisons. So I want to dig into the literature to find out what i…

It is a better investment to read about those things for a bit in my experience. It should not be scary or niche to take some time and read a textbook or a high quality paper. There is no replacement for reading textbooks or high quality papers. If you are saying that you didn't do this kind of thing anyway and now you can do it. Then I would question the definition of the action you are doing because it is not the s…

This is just "classic" (but avoidable) miscommunication. I don't even disagree with you on your point! I'm only saying you are not reading my point in the context it was offered.

For more background, please read Rapoport's Rules : https://themindcollection.com/rapoports-rules/

> Rapoport’s Rules, also known as Dennett’s Rules, is a list of four guidelines that detail how to interpret arguments charitably and criticise constructively. The concept was coined by philosopher Daniel C. Dennett in his book Intuition Pumps. Dennett acknowledged our proclivity to misinterpret and attack a counterpart’s argument instead of engaging meaningfully with what was actually said.

Post reply on HN