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

Claude 3 model family

anthropic.com

Post reply on HN
Print view View original

591–600 of 723 posts

Re: Claude 3 model family

#591

Post by exo-pla-net »

CorpOverreach wrote: post #583

This part continues to bug me in ways that I can't seem to find the right expression for: > Previous Claude models often made unnecessary refusals that suggested a lack of contextual understanding. We’ve made meaningful progress in this area: Opus, Sonnet, and Haiku are significantly less likely to refuse to answer prompts that border on the system’s guardrails than previous generations of models. As shown below, the…

They're operating under the same principle that many of us have in refusing to help engineer weaponry: we don't want other people's actions using our tools to be on our conscience.

Unfortunately, many people believe in thought crimes, and many people have Puritanical beliefs surrounding sex. There is reputational cost in not catering to these people. E.g. no funding. So this is what we're left with.

Myself I'd also like the damn models to do whatever is asked of them. If the user uses a model for crime, we have a thing called the legal system to handle that. We don't need Big Brother to also be watching for thought crimes.

Re: Claude 3 model family

#592

Post by dheera »

simonw wrote: post #189

I just released a plugin for my LLM command-line tool that adds support for the new Claude 3 models: pipx install llm llm install llm-claude-3 llm keys set claude # paste Anthropic API key here llm -m claude-3-opus '3 fun facts about pelicans' llm -m claude-3-opus '3 surprising facts about walruses' Code here: https://github.com/simonw/llm-claude-3 More on LLM: https://llm.datasette.io/

> # paste Anthropic API key here

Considering Anthropic API keys seem to be free to create I wonder if this part could be automated too using a headless chrome browser. It would be one less annoyance and allow a proliferation of other software that could just be pipped or apt-gotten and "just work" but now there's this one annoying human step.

Bonus points if when usage is nearing API limits, it uses the GPU to mine a small amount of bitcoin and use that to pay for more API capacity 100% autonomously without user intervention. We're in the AI era after all, it's about time computers did things on their own.

Re: Claude 3 model family

#593

Post by machdiamonds »

wesleyyue wrote: post #62

Just added Claude 3 to Chat at https://double.bot if anyone wants to try it for coding. Free for now and will push Claude 3 for autocomplete later this afternoon. From my early tests this seems like the first API alternative to GPT4. Huge!

Hi, what differentiates double from Cursor?

Re: Claude 3 model family

#594

Post by mattigames »

CorpOverreach wrote: post #583

This part continues to bug me in ways that I can't seem to find the right expression for: > Previous Claude models often made unnecessary refusals that suggested a lack of contextual understanding. We’ve made meaningful progress in this area: Opus, Sonnet, and Haiku are significantly less likely to refuse to answer prompts that border on the system’s guardrails than previous generations of models. As shown below, the…

You don't think that if the hammer company had a way (that cost them almost nothing) to make sure that the hammer its never used to attack human beings they wouldn't add such feature? I think many would, if anything by pressure of their local goverment or even the competition ("our hammers can't hurt your baby on accident like those other companies!") , but its impossible to add such feature to hammer; so maybe the lack of such feature its not by choice but a byproduct of its limitations.

Re: Claude 3 model family

#595

Post by bobsmooth »

vood wrote: post #585
CorpOverreach wrote: post #583

This part continues to bug me in ways that I can't seem to find the right expression for: > Previous Claude models often made unnecessary refusals that suggested a lack of contextual understanding. We’ve made meaningful progress in this area: Opus, Sonnet, and Haiku are significantly less likely to refuse to answer prompts that border on the system’s guardrails than previous generations of models. As shown below, the…

This is a weird demand to have in my opinion. You have plenty of applications on your computer and they only do what they were designed for. You can't ask a note taking app (even if it's open soured) to do video editing, unless you modify the code.

My note taking app has never refused my input of a swear word.

Re: Claude 3 model family

#596

Post by Jackson__ »

geuis wrote: post #550
j-b wrote: post #364

Opus (and all prior Claude models) still do not correctly answer the Sally question, unfortunately: Q: Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have? A: Okay, let's organize the information we have: Sally is a girl. Sally has 3 brothers. Each of Sally's brothers has 2 sisters. Now, let's think about this step by step: We know that Sally is a girl, so she is a sister to he…

Mixtral 8x7b-32768 got it on the first try: Sally has 1 sister. Here's the logic behind this: 1. We know that Sally has 3 brothers. 2. Then we are told that each brother has 2 sisters. 3. Since Sally is one of the children in the family, there must be another sister besides Sally. 4. Therefore, Sally has 1 sister. The number of sisters Sally has is not affected by the number of brothers she has, so the information ab…

I'm amazed mistral is still doing the inverse chain of thought reasoning by default, even with their new large model.

This causes it to get the question wrong for me, when testing, and only if I manually prompt normal CoT does it get it right.

Is there any papers showing a merit to this approach? It seems extremely counter-intuitive.

Re: Claude 3 model family

#597

Post by Sateeshm »

zurfer wrote: post #168
appplication wrote: post #143

Earlier quoted context omitted.

What this really says to me is the indefensibility of any current advances. There’s really cool stuff going on right now, but anyone can do it. Not to say anyone can push the limits of research, but once the cat’s out of the bag, anyone with a few $B and dozen engineers can replicate a model that’s indistinguishably good from best in class to most users.

Barrier to entry with "few $B" is pretty high. Especially since the scaling laws indicate that it's only getting more expensive. And even if you manage to raise $Bs, you still need to be clever on how to deploy it (talent, compute, data) ...

There is no meaningful network effect or vendor lock-in - which is like the #1 thing that prevents companies from competing. That's the real problem for these AI companies.

Re: Claude 3 model family

#598

Post by firestar464 »

wesleyyue wrote: post #577
wesleyyue wrote: post #255

Earlier quoted context omitted.

It's default to claude 3 right now so I could get it out quick, but working on a toggle for the front-end now to switch between the two.

for future readers, the setting is now shipped in >v0.49. The default is now back to GPT-4 as it has lower latency but you can manually change it to Claude 3 in settings if you wish to try out Anthropic's new model.

It seems that a lot of the techies here have found it easy to find settings, but I seem to have trouble with that. Would you mind assisting me?

Re: Claude 3 model family

#599

Post by dweekly »

furyofantares wrote: post #581
sigmoid10 wrote: post #505

Earlier quoted context omitted.

Did you use GPT3.5 for chat? I just tried it on vanilla ChatGPT using GPT4 with no extra stuff and it immediately gets the correct answer: "Sally has 3 brothers, and each of them has 2 sisters. The description implies that Sally's brothers are her only siblings. Therefore, the two sisters each brother has must be Sally and one other sister. This means Sally has just one sister."

ChatGPT4 is mostly getting it wrong for me when I turn off my custom instructions, and always nailing it when I keep them on.

What are your custom instructions?

Re: Claude 3 model family

#600

Post by johnfn »

CorpOverreach wrote: post #583

This part continues to bug me in ways that I can't seem to find the right expression for: > Previous Claude models often made unnecessary refusals that suggested a lack of contextual understanding. We’ve made meaningful progress in this area: Opus, Sonnet, and Haiku are significantly less likely to refuse to answer prompts that border on the system’s guardrails than previous generations of models. As shown below, the…

It's not about you. It's about Joe Drugdealer who wants to use it to learn how to make meth, or do other nefarious things.
Post reply on HN