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

901–910 of 1001 posts

Re: Claude Opus 4.6

#901

Post by kouunji »

hereonout2 wrote: post #803
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…

I was playing about with Chat GPT the other day, uploading screen shots of sheet music and asking it to convert it to ABC notation so I could make a midi file of it. The results seemed impressive until I noticed some of the "Thinking" statements in the UI. One made it apparent the model / agent / whatever had read the title from the screenshot and was off searching for existing ABC transcripts of the piece Ode to Joy…

For structured outputs like that wouldn’t it be better to get the LLM to create a script to repeatably make the translation?

Re: Claude Opus 4.6

#902

Post by yunohn »

sigmoid10 wrote: post #822
grey-area wrote: post #818

Earlier quoted context omitted.

Surely the corpus Opus 4.6 ingested would include whatever reference you used to check the spells were there. I mean, there are probably dozens of pages on the internet like this: https://www.wizardemporium.com/blog/complete-list-of-harry-p... Why is this impressive? Do you think it's actually ingesting the books and only using those as a reference? Is that how LLMs work at all? It seems more likely it's predicting t…

Most people still don't realize that general public world knowledge is not really a test for a model that was trained on general public world knowledge. I wouldn't be surprised if even proprietary content like the books themselves found their way into the training data, despite what publishers and authors may think of that. As a matter of fact, with all the special deals these companies make with publishers, it is ge…

Maybe y’all missed this?

https://www.washingtonpost.com/technology/2026/01/27/anthrop...

Anthropic, specifically, ingested libraries of books by scanning and then disposing of them.

Re: Claude Opus 4.6

#903

Post by rishabhaiover »

nopinsight wrote: post #900

Some of Opus 4.6's standout results for me: * GDPVal Elo: 1606 vs. GPT-5.2's 1462. OpenAI reported that GPT-5.2 has a 70.9% win-or-tie rate against human professionals. ( https://openai.com/index/gdpval/ ) Based on Elo math, we can estimate Opus 4.6's win-or-tie rate against human pros at 85–88%. * OSWorld: 72.7%, matching human performance at ~72.4% ( https://os-world.github.io/ ). Since the human subjects were CS s…

Agreed. These metrics + my personal use convey reliable intelligence over consistent usage. Moving forward, if context windows get bigger and token price lower, I have a hard time figuring out why your argument would be wrong.

Re: Claude Opus 4.6

#904

Post by jodrellblank »

AnimalMuppet wrote: post #474
fragmede wrote: post #341

Earlier quoted context omitted.

The estimation I did 4 months ago: > there are approximately 200k common nouns in English, and then we square that, we get 40 billion combinations. At one second per, that's ~1200 years, but then if we parallelize it on a supercomputer that can do 100,000 per second that would only take 3 days. Given that ChatGPT was trained on all of the Internet and every book written, I'm not sure that still seems infeasible. http…

But you need to also include the number of prepositions. "A pelican on a bicycle" is not at all the same as "a pelican inside a bicycle". There are estimated to be 100 or so prepositions in English. That gets you to 4 trillion combinations.

The prompt was "a pelican riding a bicycle"; not prepositions but every verb. Potentially every adverb+verb combination - "a pelican clumsily pushing a bicycle"

Re: Claude Opus 4.6

#905

Post by lgas »

setgree wrote: post #895

I asked > Can you find an academic article that _looks_ legitimate -- looks like a real journal, by researchers with what look like real academic affiliations, has been cited hundreds or thousands of times -- but is obviously nonsense, e.g. has glaring typos in the abstract, is clearly garbled or nonsensical? It pointed me to a bunch of hoaxes. I clarified: > no, I'm not looking for a hoax, or a deliberate comment on…

Well, if there are papers that match your criteria, it's hallucinating the "no".

Re: Claude Opus 4.6

#906

Post by everforward »

jama211 wrote: post #714
everforward wrote: post #588

Earlier quoted context omitted.

There are absolutely things wrong with that, because React was designed to solve problems that don't exist in a TUI. React fixes issues with the DOM being too slow to fully re-render the entire webpage every time a piece of state changes. That doesn't apply in a TUI, you can re-render TUIs faster than the monitor can refresh. There's no need to selectively re-render parts of the UI, you can just re-render the entire…

It is demonstrably absolutely fine. Sheesh.

It’s fine in the sense that it works, it’s just a really bad look for a company building a tool that’s supposed to write good code because it balloons the resources consumed up to an absurd level.

300MB of RAM for a CLI app that reads files and makes HTTP calls is crazy. A new emacs GUI instance is like 70MB and that’s for an entire text editor with a GUI.

Re: Claude Opus 4.6

#907

Post by psychoslave »

lgas wrote: post #905
setgree wrote: post #895

I asked > Can you find an academic article that _looks_ legitimate -- looks like a real journal, by researchers with what look like real academic affiliations, has been cited hundreds or thousands of times -- but is obviously nonsense, e.g. has glaring typos in the abstract, is clearly garbled or nonsensical? It pointed me to a bunch of hoaxes. I clarified: > no, I'm not looking for a hoax, or a deliberate comment on…

Well, if there are papers that match your criteria, it's hallucinating the "no".

That's still less leaned toward blatant lies like "yes, here is a list" and a doomacroll size of garbage litany.

Actually "no, this is not something within the known corpus of this LLM, or the policy of its owners prevent to disclose it" would be one of the most acceptable answer that could be delivered, which should cover most cases in honest reply.

Re: Claude Opus 4.6

#908

Post by psychoslave »

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…

Ah and no one thrown TOAC in it yet?

Re: Claude Opus 4.6

#909

Post by kgeist »

IAmGraydon wrote: post #697
ck_one wrote: post #562

Earlier quoted context omitted.

It didn't use web search. But for sure it has some internal knowledge already. It's not a perfect needle in the hay stack problem but gemini flash was much worse when I tested it last time.

I'm not sure what your knowledge level of the inner workings of LLMs is, but a model doesn't need search or even an internet connection to "know" the information if it's in its training dataset. In your example, it's almost guaranteed that the LLM isn't searching books - it's just referencing one of the hundreds of lists of those spells in it's training data. This is the LLM's magic trick that has everyone fooled int…

>The truth is it's just as far from intelligence your music playback device is from having Elvis inside of it.

A music playback device's purpose is to allow you hear Elvis' voice. A good device does it well: you hear Elvis' voice (maybe with some imperfections). Whether a real Elvis is inside of it or not, doesn't matter - its purpose is fulfilled regardless. By your analogy, an LLM simply reproduces what an intelligent person would say on the matter. If it does its job more-less, it doesn't matter either, whether it's "truly intelligent" or not, its output is already useful. I think it's completely irrelevant in both cases to the question "how well does it do X?" If you think about it, 95% we know we learned from school/environment/parents, we didn't discover it ourselves via some kind of scientific method, we just parrot what other intelligent people said before us, mostly. Maybe human "intelligence" itself is 95% parroting/basic pattern matching from training data? (18 years of training during childhood!)

Post reply on HN