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

791–800 of 1001 posts

Re: Claude 4

#791

Post by mikeshi42 »

SparkyMcUnicorn wrote: post #669
Tossrock wrote: post #309

Earlier quoted context omitted.

Are you sure you're using 4? Mine says January 2025: https://claude.ai/share/9d544e4c-253e-4d61-bdad-b5dd1c2f1a63

100% sure. Tested in the Anthropic workbench[0] to double check and got the same result. The web interface has a prompt that defines a cutoff date and who's president[1]. [0] https://console.anthropic.com/workbench [1] https://docs.anthropic.com/en/release-notes/system-prompts#c...

Can confirm the workbench does with `claude-sonnet-4-20250514` returns Biden (with a claimed April 2024 cutoff date) while Chat returns Trump (as encoded in the system prompt, with no cutoff date mention). Interesting

Re: Claude 4

#792

Post by layoric »

gr_norm wrote: post #681
layoric wrote: post #636

Earlier quoted context omitted.

There are several papers pointing towards 'thinking' output is meaningless to the final output, and using dots, or pause tokens enabling the same additional rounds of throughput result in similar improvements. So in a lot of regards the 'thinking' is mostly marketing. - "Think before you speak: Training Language Models With Pause Tokens" - https://arxiv.org/abs/2310.02226 - "Let's Think Dot by Dot: Hidden Computation…

Wow, my first ever video on AI! I'm rather disappointed. That was devoid of meaningful content save for the two minutes where they went over the Anthropic blog post on how LLMs (don't) do addition. Importantly, they didn't remotely approach what those other papers are about, or why thinking tokens aren't important for chain-of-thought. Is all AI content this kind of slop? Sorry, no offense to the above comment, it wa…

The video is just an entertaining overview, as indicated, I'm not the author of the video, it wasn't meant to be a deep dive. I linked the three related papers directly in there. I don't know how much more you are expecting from a HN comment, but this was a point in the right direction, not the definitive guide on the matter. This is a you problem.

Re: Claude 4

#793

Post by patates »

khimaros wrote: post #582
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…

i believe Gemini 2.5 Pro also does this

It does now, but I think it wasn't the case before?

Re: Claude 4

#794

Post by Davidzheng »

dbingham wrote: post #743

It feels like these new models are no longer making order of magnitude jumps, but are instead into the long tail of incremental improvements. It seems like we might be close to maxing out what the current iteration of LLMs can accomplish and we're into the diminishing returns phase. If that's the case, then I have a bad feeling for the state of our industry. My experience with LLMs is that their code does _not_ cut i…

Disagree. The marginal returns are more in places where the LLMs are near skill ceilings.

Re: Claude 4

#795

Post by weq »

paulddraper wrote: post #497
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…

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

The more popular a library is, the more times its updated every year, the more it will suffer this fate. You always have refine prompts with specific versions and specific ways of doing things, each will be different on your use case.

Re: Claude 4

#796

Post by weq »

soperj wrote: post #432
tmpz22 wrote: post #96

Earlier quoted context omitted.

And IMO it has a long way to go. There is a lot of nuance when orchestrating dependencies that can cause subtle errors in an application that are not easily remedied. For example a lot of llms (I've seen it in Gemini 2.5, and Claude 3.7) will code non-existent methods in dynamic languages. While these runtime errors are often auto-fixable, sometimes they aren't, and breaking out of an agentic workflow to deep dive th…

> if mostly because agentic coding entices us into being so lazy. Any coding I've done with Claude has been to ask it to build specific methods, if you don't understand what's actually happening, then you're building something that's unmaintainable. I feel like it's reducing typing and syntax errors, sometime it leads me down a wrong path.

I can just imagine it now, you launch your AI coded first product and get a bug in production, and the only way the AI can fix the bug is to re-write and deploy the app with a different library. Your then proceed to show the changelog to the CCB for approval including explaining the fix to the client trying to explain its risk profile for their signoff.

"Yeh, we solved the duplicate name appearing the table issue by moving databases engines and UI frameworks to ones more suited to the task"

Re: Claude 4

#797

Post by gr_norm »

layoric wrote: post #792
gr_norm wrote: post #681

Earlier quoted context omitted.

Wow, my first ever video on AI! I'm rather disappointed. That was devoid of meaningful content save for the two minutes where they went over the Anthropic blog post on how LLMs (don't) do addition. Importantly, they didn't remotely approach what those other papers are about, or why thinking tokens aren't important for chain-of-thought. Is all AI content this kind of slop? Sorry, no offense to the above comment, it wa…

The video is just an entertaining overview, as indicated, I'm not the author of the video, it wasn't meant to be a deep dive. I linked the three related papers directly in there. I don't know how much more you are expecting from a HN comment, but this was a point in the right direction, not the definitive guide on the matter. This is a you problem.

An overview of what? It's entertaining to me when I come away understanding something more than I did before. I expected a high level explanation of the papers, or the faintest intuition behind the phenomenon your comment talked about.

If you watched the video, it doesn't actually say anything besides restating variants of "thinking tokens aren't important" in a few different ways, summarizing a distantly related blog post, and entertaining some wild hypotheses about the future of LLMs. It's unclear if the producer has any deeper understanding of the subject; it honestly sounded like some low grade LLM generated fluff. I'm simply not used to that level of lack-of-substance. It wasn't a personal attack against you, as indicated.

Re: Claude 4

#798

Post by csomar »

yosito wrote: post #169
ModernMech wrote: post #66

Earlier quoted context omitted.

That's kind of my benchmark for whether or not these models are useful. I've got a project that needs some extensive refactoring to get working again. Mostly upgrading packages, but also it will require updating the code to some new language semantics that didn't exist when it was written. So far, current AI models can make essentially zero progress on this task. I'll keep trying until they can!

Personally, I don't believe AI is ever going to get to that level. I'd love to be proven wrong, but I really don't believe that an LLM is the right tool for a job that requires novel thinking about out of the ordinary problems like all the weird edge cases and poor documentation that comes up when trying to upgrade old software.

That's the easiest task for an LLM to do. Upgrading from x.y to z.y is for the most part syntax changes. The issue is that most of the documentation sucks. The LLM issue is that it doesn't have access to that documentation in the first place. Coding LLMs should interact with LSPs like humans do. You ask the LSP for all possible functions, you read the function docs and then you type from the available list of options.

LLMs can in theory do that but everyone is busy burning GPUs.

Re: Claude 4

#799

Post by csomar »

datpuz wrote: post #311
sunaookami wrote: post #193

Earlier quoted context omitted.

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

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.

I disagree. I find myself constantly going to their free offering which was able to solve lots of coding tasks that 3.7 could not.

Re: Claude 4

#800

Post by theptip »

hsn915 wrote: post #488
brookst wrote: post #451

Earlier quoted context omitted.

How much have you used Claude 4?

I asked it a few questions and it responded exactly like all the other models do. Some of the questions were difficult / very specific, and it failed in the same way all the other models failed.

Great example of this general class of reasoning failure.

“AI does badly on my test therefore it’s bad”.

The correct question to ask is, of course, what is it good at? (For bonus points, think in terms of $/task rather than simply being dominant over humans.)

Post reply on HN