Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Opus 4.6

anthropic.com

Post reply on HN
Print view View original

741–750 of 1001 posts

Re: Claude Opus 4.6

#741

Post by gbalduzzi »

matt_lo wrote: post #732
ck_one wrote: post #482

Just tested the new Opus 4.6 (1M context) on a fun needle-in-a-haystack challenge: finding every spell in all Harry Potter books. All 7 books come to ~1.75M tokens, so they don't quite fit yet. (At this rate of progress, mid-April should do it ) For now you can fit the first 4 books (~733K tokens). Results: Opus 4.6 found 49 out of 50 officially documented spells across those 4 books. The only miss was "Slugulus Eruc…

use AI to rewrite all the spells from all the books, then try to see if AI can detect the rewritten ones. This will ensure it's not pulling from it's trained data set.

Neat idea, but why should I use AI for a find and replace?

It feels like shooting a fly with a bazooka

Re: Claude Opus 4.6

#742

Post by TheDong »

margalabargala wrote: post #170
eaf7e281 wrote: post #99

Earlier quoted context omitted.

There's no way they actually work on training this.

I suspect they're training on this. I asked Opus 4.6 for a pelican riding a recumbent bicycle and got this. https://i.imgur.com/UvlEBs8.png

I don't think that really proves anything, it's unsurprising that recumbent bicycles are represented less in the training data and so it's less able to produce them.

Try something that's roughly equally popular, like a Turkey riding a Scooter, or a Yak driving a Tractor.

Re: Claude Opus 4.6

#743

Post by jaco6 »

rvz wrote: post #539
meroes wrote: post #521

Earlier quoted context omitted.

What is this supposed to show exactly? Those books have been feed into LLMs for years and there's even likely specific RLHF's on extracting spells from HP.

> What is this supposed to show exactly? Nothing. You can be sure that this was already known in the training data of PDFs, books and websites that Anthropic scraped to train Claude on; hence 'documented'. This is why tests like what the OP just did is meaningless. Such "benchmarks" are performative to VCs and they do not ask why isn't the research and testing itself done independently but is almost always done by th…

[dead]

Re: Claude Opus 4.6

#744

Post by ra »

danielbln wrote: post #706
ra wrote: post #585

Why are Anthropic such a horrible company to deal with?

Care to elaborate?

obscure billing, unreachable customer support gatekeeped by an overzealous chatbot, no transparency about inclusions, or changes to inclusions over time... just from recent experience.

Re: Claude Opus 4.6

#745

Post by cryptoegorophy »

bobbylarrybobby wrote: post #729
legitster wrote: post #72

I'm still not sure I understand Anthropic's general strategy right now. They are doing these broad marketing programs trying to take on ChatGPT for "normies". And yet their bread and butter is still clearly coding. Meanwhile, Claude's general use cases are... fine. For generic research topics, I find that ChatGPT and Gemini run circles around it: in the depth of research, the type of tasks it can handle, and the qual…

I really like that Claude feels transactional. It answers my question quickly and concisely and then shuts up. I don't need the LLM I use to act like my best friend.

Then why are they advertising to people that are complete opposite of you? Why couldn’t they just … ask LLM what their target audience is?

Re: Claude Opus 4.6

#746

Post by miohtama »

gbalduzzi wrote: post #741
matt_lo wrote: post #732

Earlier quoted context omitted.

use AI to rewrite all the spells from all the books, then try to see if AI can detect the rewritten ones. This will ensure it's not pulling from it's trained data set.

Neat idea, but why should I use AI for a find and replace? It feels like shooting a fly with a bazooka

Bazooka guarantees the hit

Re: Claude Opus 4.6

#748

Post by ptsd_dalmatian »

rahulroy wrote: post #451

They are also giving away $50 extra pay as you go credit to try Opus 4.6. I just claimed it from the web usage page[1]. Are they anticipating higher token usage for the model or just want to promote the usage? [1] https://claude.ai/settings/usage

Based on email from Antrhopic, I’ve expected to get this automatically. I’ve met their conditions. Searching this thread for “50” got me to your comment and link worked. Thanks HN friend!

Re: Claude Opus 4.6

#749

Post by rahulroy »

thunfischtoast wrote: post #497
rahulroy wrote: post #451

They are also giving away $50 extra pay as you go credit to try Opus 4.6. I just claimed it from the web usage page[1]. Are they anticipating higher token usage for the model or just want to promote the usage? [1] https://claude.ai/settings/usage

Thanks for the tip!

Glad that it was helpful. Thanks

Re: Claude Opus 4.6

#750

Post by rahulroy »

ptsd_dalmatian wrote: post #748
rahulroy wrote: post #451

They are also giving away $50 extra pay as you go credit to try Opus 4.6. I just claimed it from the web usage page[1]. Are they anticipating higher token usage for the model or just want to promote the usage? [1] https://claude.ai/settings/usage

Based on email from Antrhopic, I’ve expected to get this automatically. I’ve met their conditions. Searching this thread for “50” got me to your comment and link worked. Thanks HN friend!

Haha! Glad it was helpful. Yes, I keep an eye on that page, so I was quick to notice.
Post reply on HN