Why is Anthropic's public writing style so unlike Claude's?
cmart.blog
cmart.blog
Anthropic certainly isn't planning to take responsibility for Claude's mistakes - that's the user's responsibility. Describing everything as 'collaborating' is I think part of their efforts to emphasise the user's role in the process.
I trust the output of colleagues I am collaborating with and have an assumption of some shared responsibility. But if I use a tool like numpy/matplotlib then I am accountable for the conclusions I come up with. I can't make an excuse that "matplotlib" created a plot so my decisions were incorrect and not due to my own negligence.
Silicon Valley Executives Are Tech Fans. Just Not for Their Kids
Every damn Claude article does the “tell ‘em what you’re going to tell ‘em, tell ‘em, tell ‘em what you told ‘em” routine.
The real way to actually get a good output has always been in the prompt, not these parameters
No, I do not. Good for me I guess.
> The real way to actually get a good output has always been in the prompt, not these parameters
What an absurd claim.
Meanwhile you clearly have zero clue what you are talking about because a simple Google search would show you otherwise but that must be too difficult for you
Which is kinda sad, if you've used Anthropic products, because you could get comparable performance from cheaper models for vast majority of tasks.
> No, they don't. That's the whole point.
Bad for them; do not use Anthropic then. Besides "the whole point" of conversation you have interrupted is that "low temperature and tight sampling produces stiff boring cliche prose" - which is truism, as those settings control the entropy of the output. And it is utterly irrelevant frankly if one has access to the Claude sampler through API or not; as Anthropic has apparently locked the sampler at very conservative temperature (probably as low as 0.2), there is no way to squeeze god prose out of it, as the logits have been severely messed up wrt to the actual word distribution in standard English.
They aren't even available for the new Claude models which we use extensively so I think that should tell you something. I've made over $6 million with my AI app in the last few years without worrying about temperature and other parameters. What have you done?
Oh, wow.
> without worrying about temperature and other parameters.
Tells a lot about you.
And they probably know basic LLM tricks like "write it in the style of X".
When you read a blog post with Claude voice, you're seeing the result of someone who couldn't even be bothered to do that which is why they deserve extra lashings.
/s?