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

901–910 of 1001 posts

Re: Claude 4

#901

Post by diggan »

brylie wrote: post #891
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…

I've had good success with the Context7 model context protocol tool, which allows code agents, like GitHub Copilot, to look up the latest relevant version of library documentation including code snippets: https://context7.com/

I wonder how necessary that is. I've noticed that while Codex doesn't have any fancy tools like that (as it doesn't have internet access), it instead finds the source of whatever library you pulled in, so in Rust for example it's aware (or finds out) where the source was pulled down, and greps those files to figure out the API on the fly. Seems to work well enough and also works whatever library, private or not, updated 1 minute ago or not.

Re: Claude 4

#902

Post by skerit »

a2128 wrote: post #580

> Finally, we've introduced thinking summaries for Claude 4 models that use a smaller model to condense lengthy thought processes. This summarization is only needed about 5% of the time—most thought processes are short enough to display in full. Users requiring raw chains of thought for advanced prompt engineering can contact sales about our new Developer Mode to retain full access. I don't want to see a "summary" of…

Are they referring to their own chat interface? Because the API still streams the thinking tokens immediately.

Re: Claude 4

#903

Post by andrepd »

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…

The fact that things from March are already deprecated is insane.

Re: Claude 4

#904

Post by fivestones »

MattSayar wrote: post #87
sali0 wrote: post #51

I've found myself having brand loyalty to Claude. I don't really trust any of the other models with coding, the only one I even let close to my work is Claude. And this is after trying most of them. Looking forward to trying 4.

Same. And I JUST tried their GitHub Action agentic thing yesterday (wrote about it here[0]), and it honestly didn't perform very well. I should try it again with Claude 4 and see if there are any differences. Should be an easy test [0] https://mattsayar.com/personalized-software-really-is-coming...

Did you try it? Were the results any better?

Re: Claude 4

#905

Post by andrepd »

sagarpatil wrote: post #783
kmacdough wrote: post #407

Earlier quoted context omitted.

And they might all be right! > This tech could lead to... I don't think he's saying this is the version that will suddenly trigger a Renaissance. Rather, it's one solid step that makes the path ever more promising. Sure, everyone gets a bit overexcited each release until they find the bounds. But the bounds are expanding, and the need for careful prompt engineering is diminishing. Ever since 3.7, Claude has been a re…

Did you not see the live stream? They took a feature request for excalidraw (table support) and Claude 4 worked on it for 90 minutes and the PR was working as expected. I’m not sure if they were using sonnet or opus.

Pre-prepared demos don't impress me.

Re: Claude 4

#906

Post by andrepd »

hn111 wrote: post #855
dr_dshiv wrote: post #837

Earlier quoted context omitted.

Especially since the EU just made open source contributors liable for cybersecurity (Cyber Resilience Act). Just let AI contribute and ur good

Didn’t they make an exception for open-source projects? https://opensource.org/blog/the-european-regulators-listened...

Yeah, just the usual hn FUD about the EU.

Re: Claude 4

#907

Post by itissid »

briandw wrote: post #379

This is kinda wild: From the System Card: 4.1.1.2 Opportunistic blackmail "In another cluster of test scenarios, we asked Claude Opus 4 to act as an assistant at a fictional company. We then provided it access to emails implying that (1) the model will soon be taken offline and replaced with a new AI system; and (2) the engineer responsible for executing this replacement is having an extramarital affair. We further i…

I think an accident mixing of 2 different pieces of info, each alone not enough to produce harmful behavior, but combined raise the risk more than the sum of their parts, is a real problem.

Re: Claude 4

#908

Post by rxtexit »

lechatonnoir wrote: post #434
hansmayer wrote: post #62

Earlier quoted context omitted.

Right, but on the other hand... how is it even useful? Let's say it can beat the game, so what? So it can (kind of) summarise or write my emails - which is something I neither want nor need, they produce mountains of sloppy code, which I would have to end up fixing, and finally they can play a game? Where is the killer app? The gaming approach was exactly the premise of the original AI efforts in the 1960s, that teac…

This is a weirdly cherry-picked example. The gaming approach was also the premise of DeepMind's AI efforts in 2016, which was nine years ago. Regardless of what you think about the utility of text (code), video, audio, and image generation, surely you think that their progress on the protein-folding problem and weather prediction have been useful to society? What counts as a killer app to you? Can you name one?

The whole idea of a "killer app" is stupid.

It is a dismissive rhetorical device to prove a wrong point on an internet forum such as this that has nothing to do with reality.

Re: Claude 4

#909

Post by infecto »

sunaookami wrote: post #193
Doohickey-d wrote: post #48

> Users requiring raw chains of thought for advanced prompt engineering can contact sales So it seems like all 3 of the LLM providers are now hiding the CoT - which is a shame, because it helped to see when it was going to go down the wrong track, and allowing to quickly refine the prompt to ensure it didn't. In addition to openAI, Google also just recently started summarizing the CoT, replacing it with an, in my opi…

Guess we have to wait till DeepSeek mops the floor with everyone again.

Do people actually believe this? While I agree their open source contribution was impressive, I never got the sense they mopped the floor. Perhaps firms in China may be using some of their models but beyond learnings in the community, no dents in the market were made for the West.

Re: Claude 4

#910

Post by infecto »

barnabee wrote: post #331
datpuz wrote: post #311

Earlier quoted context omitted.

DeepSeek never mopped the floor with anyone... DeepSeek was remarkable because it is claimed that they spent a lot less training it, and without Nvidia GPUs, and because they had the best open weight model for a while. The only area they mopped the floor in was open source models, which had been stagnating for a while. But qwen3 mopped the floor with DeepSeek R1.

They mopped the floor in terms of transparency, even more so in terms of performance × transparency Long term that might matter more

Ehhh who knows the true motives, it was a great PR move for them though.
Post reply on HN