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

961–970 of 1001 posts

Re: Claude 4

#961

Post by MollyRealized »

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…

> whereas the history of the US civil war can probably be updated less frequently.

Depends on which one you're talking about.

Re: Claude 4

#962

Post by 999900000999 »

bckr wrote: post #949
999900000999 wrote: post #686

Question: Should I ask it to update an existing project largely written in 3.7 or ask it to start from scratch? I keep running into an issue where an LLM will get like 75% of a solution working and then the last 25% is somehow impossible to get right. I don’t expect perfection, but I’ve wasted so much time vibe coding this thing I guess I’d do better to actually program

Update the old code, but make sure you’re using short ( You have to guide these models. Vibe coding does not work.

I don't expect to be able to git clone the Linux kernel, write "claude make it good" and fix everything.

I do expect these tools to be to able to understand they code they write through. Writing new code is very easy. Maintaining code is hard.

So far I'm very disappointed compared to how hyped this tech is. Although, I'm happy to have a job and if these coding models lived up to their promise I don't think I would have one.

Re: Claude 4

#963

Post by zarathustreal »

gkfasdfasdf wrote: post #939
_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.

Just curious, how do you know your questions and the SQL aren't in the LLM training data? Looks like the benchmark questions w/SQL are online ( https://ghe.clickhouse.tech/ ).

“Your model has memorized all knowledge, how do you know it’s smart?”

Re: Claude 4

#964

Post by kofman »

modeless wrote: post #5

Ooh, VS Code integration for Claude Code sounds nice. I do feel like Claude Code works better than the native Cursor agent mode. Edit: How do you install it? Running `/ide` says "Make sure your IDE has the Claude Code extension", where do you get that?

Let us know if you were able to get it installed. You need to run claude inside the vscode (or cursor/windsurf) terminal for it to auto-install.

Re: Claude 4

#965

Post by pantsforbirds »

hsn915 wrote: post #416

I can't be the only one who thinks this version is no better than the previous one, and that LLMs have basically reached a plateau, and all the new releases "feature" are more or less just gimmicks.

It seems MUCH better at tool usage. Just had an example where I asked Sonnet 4 to split a PR I had after we had to revert an upstream commit.

I didn't want to lose the work I had done, and I knew it would be a pain to do it manually with git. The model did a fantastic job of iterating through the git commits and deciding what to put into each branch. It got everything right except for a single test that I was able to easily move to the correct branch myself.

Re: Claude 4

#966

Post by KennyBlanken »

layoric wrote: post #622
TechDebtDevin wrote: post #467

Earlier quoted context omitted.

I think they are just getting better at the edges, MCP/Tool Calls, structured output. This definitely isn't increased intelligence, but it an increase in the value add, not sure the value added equates to training costs or company valuations though. In all reality, I have zero clue how any of these companies remain sustainable. I've tried to host some inference on cloud GPUs and its seems like it would be extremely c…

> how any of these companies remain sustainable They don't, they have a big bag of money they are burning through, and working to raise more. Anthropic is in a better position cause they don't have the majority of the public using their free-tier. But, AFAICT, none of the big players are profitable, some might get there, but likely through verticals rather than just model access.

If your house is on fire, the fact that the village are throwing firewood through the windows doesn't really mean the house will stay standing longer.

Re: Claude 4

#967

Post by jbellis »

tptacek wrote: post #150
jbellis wrote: post #94

Earlier quoted context omitted.

not sure wym, it's in the headline of the article that Opus 4 has 200k context (same as sonnet 3.7 with the beta header)

We might be looking at different articles? The string "200" appears nowhere in this one --- or I'm just wrong! But thanks!

My mistake, I was in fact looking at one of the linked details pages

Re: Claude 4

#968

Post by aqfamnzc »

otabdeveloper4 wrote: post #958
andrepd wrote: post #915

Earlier quoted context omitted.

I have no idea what this means, can someone give the eli5?

I don't either, but chain of thought is obviously bullshit and just more LLM hallucination. LLMs will routinely "reason" through a solution and then proceed to give out a final answer that is completely unrelated to the preceding "reasoning".

It's more hallucination in the sense that all LLM output is hallucination. CoT is not "what the llm is thinking". I think of it as just creating more context/prompt for itself on the fly, so that when it comes up with a final response it has all that reasoning in its context window.

Re: Claude 4

#969

Post by lanstin »

iLoveOncall wrote: post #645
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.

Web search isn't desirable or even an option in a lot of use cases that involve GenAI. It seems people have turned GenAI into coding assistants only and forget that they can actually be used for other projects too.

That's because between the two approaches "explain me this thing" or "write code to demonstrate this thing" the LLMs are much more useful on the second path. I can ask it to calculate some third derivatives, or I can ask it to write Mathematica notebook to calculate the same derivatives, and the latter is generally correct and extremely useful as is - the former requires me to scrutinize each line of logic and calculation very carefully.

It's like https://www.youtube.com/watch?v=zZr54G7ec7A where Prof. Tao uses claude to generate Lean4 proofs (which are then verifiable by machine). Great progress, very useful. While the LLM only approachs are still lacking utility for the top minds: https://mathstodon.xyz/@tao/113132502735585408

Re: Claude 4

#970

Post by runjake »

vFunct wrote: post #138
runjake wrote: post #81

Earlier quoted context omitted.

My advice: don't jump around between LLMs for a given project. The AI space is progressing too rapidly right now. Save yourself the sanity.

Each model has their own strength and weaknesses tho. You really shouldn’t be using one model for everything. Like, Claude is great at coding but is expensive so you wouldn’t use them for debugging to writing test benches. But the OpenAI models suck at architecture but are cheap, so are ideal for test benches, for example.

You did not read what I said:

> don't jump around between LLMs for a given project

I didn't say anything about sticking to a single model for every project.

Post reply on HN