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

381–390 of 1001 posts

Re: Claude 4

#381

Post by alasano »

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 context7 MCP helps with this but I agree.

Re: Claude 4

#382

Post by egamirorrim »

Rudybega wrote: post #198
minimaxir wrote: post #102

Earlier quoted context omitted.

Context window is unchanged for Sonnet. (200k in/64k out): https://docs.anthropic.com/en/docs/about-claude/models/overv... In practice, the 1M context of Gemini 2.5 isn't that much of a differentiator because larger context has diminishing returns on adherence to later tokens.

I'm going to have to heavily disagree. Gemini 2.5 Pro has super impressive performance on large context problems. I routinely drive it up to 4-500k tokens in my coding agent. It's the only model where that much context produces even remotely useful results. I think it also crushes most of the benchmarks for long context performance. I believe on MRCR (multi round coreference resolution) it beats pretty much any other…

OOI what coding agent are you managing to get to work nicely with G2.5 Pro?

Re: Claude 4

#384

Post by landl0rd »

gokhan wrote: post #250

Interesting alignment notes from Opus 4: https://x.com/sleepinyourhat/status/1925593359374328272 "Be careful about telling Opus to ‘be bold’ or ‘take initiative’ when you’ve given it access to real-world-facing tools...If it thinks you’re doing something egregiously immoral, for example, like faking data in a pharmaceutical trial, it will use command-line tools to contact the press, contact regulators, try to lock yo…

This is pretty horrifying. I sometimes try using AI for ochem work. I have had every single "frontier model" mistakenly believe that some random amine was a controlled substance. This could get people jailed or killed in SWAT raids and is the closest to "dangerous AI" I have ever seen actually materialize.

Re: Claude 4

#385

Post by devinprater »

claude.ai still isn't as accessible to me as a blind person using a screen reader as ChatGPT, or even Gemini, is, so I'll stick with the other models.

Re: Claude 4

#386

Post by dawnerd »

liorn wrote: post #233
minimaxir wrote: post #118

An important note not mentioned in this announcement is that Claude 4's training cutoff date is March 2025, which is the latest of any recent model. (Gemini 2.5 has a cutoff of January 2025) https://docs.anthropic.com/en/docs/about-claude/models/overv...

I asked it about Tailwind CSS (since I had problems with Claude not aware of Tailwind 4): > Which version of tailwind css do you know? > I have knowledge of Tailwind CSS up to version 3.4, which was the latest stable version as of my knowledge cutoff in January 2025.

I did the same recently with copilot and it of course lied and said it knew about v4. Hard to trust any of them.

Re: Claude 4

#388

Post by alasano »

Rudybega wrote: post #198
minimaxir wrote: post #102

Earlier quoted context omitted.

Context window is unchanged for Sonnet. (200k in/64k out): https://docs.anthropic.com/en/docs/about-claude/models/overv... In practice, the 1M context of Gemini 2.5 isn't that much of a differentiator because larger context has diminishing returns on adherence to later tokens.

I'm going to have to heavily disagree. Gemini 2.5 Pro has super impressive performance on large context problems. I routinely drive it up to 4-500k tokens in my coding agent. It's the only model where that much context produces even remotely useful results. I think it also crushes most of the benchmarks for long context performance. I believe on MRCR (multi round coreference resolution) it beats pretty much any other…

I find that it consistently breaks around that exact range you specified. In the sense that reliability falls off a cliff, even though I've used it successfully close to the 1M token limit.

At 500k+ I will define a task and it will suddenly panic and go back to a previous task that we just fully completed.

Re: Claude 4

#389

Post by morkalork »

rokkamokka wrote: post #142
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.

Isn't that an argument to jump around? Since performance improves so rapidly between models

I think the idea is you might end up spending your time shaving a yak. Finish your project, then try the ne SOTA on your next task.

Re: Claude 4

#390

Post by aziaziazi »

toomuchtodo wrote: post #361
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…

Does repo/package specific MCP solve for this at all?

Kind of but not in the same way: the MCP option will increase the discussion context, the training option does not. Armchair expert so confirmation would be appreciated.
Post reply on HN