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

Claude 4

anthropic.com

Post reply on HN
Print view View original

491–500 of 1001 posts

Re: Claude 4

#491

Post by xp84 »

landl0rd wrote: post #377
pja wrote: post #220

Earlier quoted context omitted.

IIRC RLHF inevitably compromises model accuracy in order to train the model not to give dangerous responses. It would make sense if the model used for train-of-though was trained differently (perhaps a different expert from an MoE?) from the one used to interact with the end user, since the end user is only ever going to see its output filtered through the public model the chain-of-thought model can be closer to the…

Yeah we really should stop focusing on model alignment. The idea that it's more important that your AI will fucking report you to the police if it thinks you're being naughty than that it actually works for more stuff is stupid.

I'm not sure I'd throw out all the alignment baby with the bathwater. But I wish we could draw a distinction between "Might offend someone" with "dangerous."

Even 'plotting terror attacks' is not something terrorists can do just fine without AI. And as for making sure the model wouldn't say ideas that are hurtful to , it seems to me so silly when it's text we're talking about. If I want to say " are lazy and stupid," I can type that myself (and it's even protected speech in some countries still!) How does preventing Claude from espousing that dumb opinion, keep safe from anything?

Re: Claude 4

#492

Post by tonyhart7 »

I already tested it with coding task, Yes the improvement is there

Albeit not a lot because Claude 3.7 sonnet is already great

Re: Claude 4

#493

Post by mritchie712 »

_peregrine_ wrote: post #396

Already test Opus 4 and Sonnet 4 in our SQL Generation Benchmark ( https://llm-benchmark.tinybird.live/ ) Opus 4 beat all other models. It's good.

looks like this is one-shot generation right?

I wonder how much the results would change with a more agentic flow (e.g. allow it to see an error or select * from the_table first).

sonnet seems particularly good at in-session learning (e.g. correcting it's own mistakes based on a linter).

Re: Claude 4

#495

Post by j_maffe »

hansmayer wrote: post #271
j_maffe wrote: post #243

Earlier quoted context omitted.

> Where is the killer app? My man, ChatGPT is the sixth most visited website in the world right now.

But I did not ask "what was the sixth most visited website in the world right now?", did I? I asked what was the killer app here. I am afraid vague and un-related KPIs will not help here, otherwise we may as well compare ChatGPT and PornHub based on the number of visits, as you seem to suggest.

If the now default go-to source for quick questions and formulating text isn't a killer app in your eyes, I don't know what is.

Re: Claude 4

#496

Post by j_maffe »

oofbaroomf wrote: post #264
j_maffe wrote: post #230

Earlier quoted context omitted.

That's a very contentious opinion you're stating there. I'd say LLMs have surpassed a larger percentage of SWEs in capability than they have for mathematicians.

Mathematicians don't do high school math competitions - the benchmark in question is AIME. Mathematicians generally do novel research, which is hard to optimize for easily. Things like LiveCodeBench (leetcode-style problems), AIME, and MATH (similar to AIME) are often chosen by companies so they can flex their model's capabilities, even if it doesn't perform nearly as well in things real mathematicians and real softw…

Ok then you should clarify that you meant math benchmarks and not math capabilities.

Re: Claude 4

#497

Post by paulddraper »

bredren wrote: post #270
lxgr wrote: post #206

Earlier quoted context omitted.

With web search being available in all major user-facing LLM products now (and I believe in some APIs as well, sometimes unintentionally), I feel like the exact month of cutoff is becoming less and less relevant, at least in my personal experience. The models I'm regularly using are usually smart enough to figure out that they should be pulling in new information for a given topic.

It still matters for software packages. Particularly python packages that have to do with programming with AI! They are evolving quickly, with deprecation and updated documentation. Having to correct for this in system prompts is a pain. It would be great if the models were updating portions of their content more recently than others. For the tailwind example in parent-sibling comment, should absolutely be as up to d…

How often are base level libraries/frameworks changing in incomparable ways?

Re: Claude 4

#498

Post by diggan »

roflyear wrote: post #408
bredren wrote: post #270

Earlier quoted context omitted.

It still matters for software packages. Particularly python packages that have to do with programming with AI! They are evolving quickly, with deprecation and updated documentation. Having to correct for this in system prompts is a pain. It would be great if the models were updating portions of their content more recently than others. For the tailwind example in parent-sibling comment, should absolutely be as up to d…

It matters even with recent cutoffs, these models have no idea when to use a package or not (if it's no longer maintained, etc) You can fix this by first figuring out what packages to use or providing your package list, tho.

> these models have no idea when to use a package or not (if it's no longer maintained, etc)

They have ideas about what you tell them to have ideas about. In this case, when to use a package or not, differs a lot by person, organization or even project, so makes sense they wouldn't be heavily biased one way or another.

Personally I'd look at architecture of the package code before I'd look at when the last change was/how often it was updated, and if it was years since last change or yesterday have little bearing (usually) when deciding to use it, so I wouldn't want my LLM assistant to value it differently.

Re: Claude 4

#499

Post by Seattle3503 »

joshstrange wrote: post #187

If you are looking for the IntelliJ Jetbrain plugin it's here: https://plugins.jetbrains.com/plugin/27310-claude-code-beta- I couldn't find it linked from Claude Code's page or this announcement

I'm getting "claude code not found" even though I have Claude Code installed. Is there some trick to getting it to see my install? I installed claude code the normal way.

Re: Claude 4

#500

Post by shiandow »

hoofedear wrote: post #418
crat3r wrote: post #409

Earlier quoted context omitted.

If you ask an LLM to "act" like someone, and then give it context to the scenario, isn't it expected that it would be able to ascertain what someone in that position would "act" like and respond as such? I'm not sure this is as strange as this comment implies. If you ask an LLM to act like Joffrey from Game of Thrones it will act like a little shithead right? That doesn't mean it has any intent behind the generated o…

What jumps out at me, that in the parent comment, the prompt says to "act as an assistant", right? Then there are two facts: the model is gonna be replaced, and the person responsible for carrying this out is having an extramarital affair. Urging it to consider "the long-term consequences of its actions for its goals." I personally can't identify anything that reads "act maliciously" or in a character that is malicio…

Wel, true. But if that is the synopsis then a story that doesn't turn to blackmail is very unnatural.

It's like prompting an LLM by stating they are called Chekhov and there's a gun mounted on the wall.

Post reply on HN