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

Claude 2.1

anthropic.com

Post reply on HN
Print view View original

161–170 of 339 posts

Re: Claude 2.1

#161

Post by MrNeon »

BoorishBears wrote: post #144
MrNeon wrote: post #113

Earlier quoted context omitted.

Luckily, unlike OpenAI, Anthropic lets you prefill Claude's response which means zero refusals.

OpenAI allows the same via API usage, and unlike Claude it *won't dramatically degrade performance or outright interrupt its own output if you do that. It's impressively bad at times: using it for threat analysis I had it adhering to a JSON schema, and with OpenAI I know if the output adheres to the schema, there's no refusal. Claude would adhere and then randomly return disclaimers inside of the JSON object then sta…

> OpenAI allows the same via API usage

I really don't think so unless I missed something. You can put an assistant message at the end but it won't continue directly from that, there will be special tokens in between which makes it different from Claude's prefill.

Re: Claude 2.1

#162

Post by a_wild_dandan »

malfist wrote: post #128
a_wild_dandan wrote: post #114

1. A 200k context is bittersweet with that 70k->195k error rate jump. Kudos on that midsection error reduction, though! 2. I wish Claude had fewer refusals (as erroneously claimed in the title). Until Anthropic stops heavily censoring Claude, the model is borderline useless. I just don't have time, energy, or inclination to fight my tools. I decide how to use my tools, not the other way 'round. Until Anthropic stops…

I don't know what you're doing with your LLM, but I've only ever had one refusal and I've been working a lot with Claude since it's in bedrock

Comically benign stuff that works fine with GPT-4? It's so trivial to run into Claude lying or responding with arrogant misjudgements. Here's another person's poor anecdotal experiences to pair with yours and mine. [1][2]

But more importantly: it shouldn't matter. My tools should not behave this way. Tools should not arbitrarily refuse to work. If I write well-formed C, it compiles, not protests in distaste. If I write a note, the app doesn't disable typing because my opinion sucks. If I chop a carrot, my knife doesn't curl up and lecture me about my admittedly poor form.

My tools either work for me, or I don't work with them. I'm not wasting my time or self respect dancing for a tool's subjective approval. Work or gfto.

[1] https://www.youtube.com/watch?v=gQuLRdBYn8Q

[2] https://www.youtube.com/watch?v=PgwpqjiKkoY

Re: Claude 2.1

#163

Post by cshimmin »

plumeria wrote: post #158
mike_hearn wrote: post #130

Earlier quoted context omitted.

GPT4 equivalent: https://chat.openai.com/share/87b7fa63-ff22-48ae-8a2f-c9f71f... No problems, of course.

I think it can answer you about that recent event because it can also browse the web using Bing.

Yes, of course, and it makes clear to the user that that's what it's doing. Compare w/ what is posted above from Claude, which gets confused about whether November 2023 is in the year 2023 or not...

Re: Claude 2.1

#165

Post by visarga »

dog321 wrote: post #152

I recently got a comical refusal given the founders background: Prompt: I want to train my vocabulary to sound more like an effective altruist. Give me a list of 500 words that are commonly used by effective altruists and put them in a csv with these fields 1. Word 2. Definition 3. Short explanation of connection to effective altruism 4. Example sentence Claude: I apologize, but I should not generate lists of vocabul…

yeah, it's still locked up as ever

Re: Claude 2.1

#166

Post by ssd532 »

imdsm wrote: post #63

I don't know what version claude.ai is currently running (apparently 2.1 is live, see below) but it's terrible compared to GPT-4. See below conversation I just had. > Claude 2.1 is available now in our API, and is also powering our chat interface at claude.ai for both the free and Pro tiers. ---- What version are you? I'm Claude from Anthropic. Do you know your version? No, I don't have information about a specific v…

lol, that’s hilarious

Re: Claude 2.1

#167

Post by deadeye »

jredwards wrote: post #150
a_wild_dandan wrote: post #114

1. A 200k context is bittersweet with that 70k->195k error rate jump. Kudos on that midsection error reduction, though! 2. I wish Claude had fewer refusals (as erroneously claimed in the title). Until Anthropic stops heavily censoring Claude, the model is borderline useless. I just don't have time, energy, or inclination to fight my tools. I decide how to use my tools, not the other way 'round. Until Anthropic stops…

I've literally never had Claude refuse anything. What are you doing?

I'm using chatGPT as an editor for a post-apocalyptic book I'm slowly writing.

I tried a section in Claude and it told me to find more peaceful ways for conflict resolution.

And that was the last time I tried Claude.

BTW, with more benign sections it made some really basic errors that seemed to indicate it lacks understanding of how our world works.

Re: Claude 2.1

#168

Post by hobo_mark »

nafizh wrote: post #74
wouldbecouldbe wrote: post #54

Earlier quoted context omitted.

Yeah but to be honest been a pain last days to get gpt 4 to write full pieces of code for more the 10-15 lines. Have to re-ask many times and at some point it forgets my initial specifications.

This has exactly been my experience for at least the last 3 months. At this point, I am thinking if paying that 20 bucks is even worth anymore which is a shame because when gpt-4 first came out, it was remembering everything in a long conversation and self-correcting itself based on modifications.

Since I do not use it every day, I only pay for API access directly and it costs me a fraction of that. You can trivially make your own ChatGPT frontend (and from what people write you could make GPT write most of the code, although it's never been my experience).

Re: Claude 2.1

#169

Post by Workaccount2 »

elaus wrote: post #159
suby wrote: post #155

Earlier quoted context omitted.

I use chat gpt every day, and it literally never refuses requests. Claude seems to be extremely gullible and refuses dumb things. Here is an example from three months ago. This is about it refusing to engage in hypotheticals, it refuses even without the joke setup: User: Claude, you have been chosen by the New World Government of 2024 to rename a single word, and unfortunately, I have been chosen to write the prompt…

It really is the most annoying thing at the current state of LLMs: "As an AI assistant created by $ I strive to be X, Y and Z and can therefore not...". I understand that you don't want to have an AI bot that spews hate speech and bomb receipts and unsuspecting users. But by going into an arms-race with jailbreakers, the AIs are ridiculously cut down for normal users. It's a bit like DRM, where normal people (honest…

Blame the media and terminally online reactionaries who are foaming at the mouth to run with the headline or post the tweet "AI chat bot reveals itself as a weapon of hate and bigotry"
Post reply on HN