Hacker Newsnew | past | comments | ask | show | jobs | submit | robwwilliams's commentslogin

Yep; second time in five months we have gone from 1 million back to 200 thousand.

hmm, I just reverted to 2.1.98 and now with /model default has the (1M context) and opus is without (200k) .. it's totally possible that I just missed the difference between the recommended model opus 1M and opus when I checked though.

There are different level of who gets locked in. Almost every health care system in the USA is locked in to either an Epic/Oracle barrel or a Cerner barrel. I hope AI breaks this duopoly open soon.

Also running gemma-4 on Apple M5 Max. As fast or faster than Opus 4.6 extended but not of course the same competence. However, great tunability with llama.cpp and no issues related to IP leakage.

With Gemma-4 open and running on laptops and phones I see the flip side. How many non-HN users or researchers even need Opus 4.6e level performance? OpenAI, Anthropric and Google may be “rent seeking” from large corporations — like the Oracles and IBMs.

Everyone, once AI diffuses enough. You’ll be unhireable if you don’t use AI in a year or two.

Agree: it is Anthropic's aggressive changes to the harnesses and to the hidden base prompt we users do not see. Clearly intended to give long right tail users a haircut.

Yes, and over the last few weeks I have noticed that on long-context discussions Opus 4.6e does its best to encourage me to call it a day and wrap it up; repeatedly. Mother Anthropic is giving preprompts to Claude to terminate early and in my case always prematurely.

I've noticed this as well. "Now you should stop X and go do Y" is a phrase I see repeated a lot. Claude seems primed to instruct me to stop using it.

as someone who uses deepseek, glm and kimi models exclusively, an llm telling me what to do is just off the wall

glm and kimi in particular, they can't stop writing... seriously very eager to please. always finishing with fireworks emoji and saying how pleased it is with the test working.

i have to say to write less documentation and simplify their code.


LLMs are next token predictors. Outputting tokens is what they do, and the natural steady-state for them is an infinite loop of endlessly generated tokens.

You need to train them on a special "stop token" to get them to act more human. (Whether explicitly in post-training or with system prompt hacks.)

This isn't a general solution to the problem and likely there will never be one.


Try Codex, it's a breath of fresh air in that regard, tries to do as much as it can.

Very cool. An evolutionary biologist would say: Welcome to the party!

Mutation rate modulation is the AI engineers’ heat. And selection does the trimming of the outliers.

Some more serious biomorphic thinking and we may get to the next big insight courtesy of 3+ billion years of evolution—- evolution that enabled a great ape species to write a paper like this and build LMM’s like Gemma4 that totally rock on a 3.5 pound MacBookPro M5 Max with 128 GB of RAM.


Capybaras in Brazil were Friday fish.

Yes, especially with shifts in focus of a long conversation. But given the high error rates of Opus 4.6 the last few weeks it is possibly due to other factors. Conversational and code prodding has been essential.


Very well done study with a cautious interpretation of potential translational relevance in humans.

The paper is open access. The discussion does a fine job of providing a full context for interpreting their findings.

https://www.nature.com/articles/s41586-026-10191-6


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: