alt Hacker NewsAI will ultimately prove better at generating the kind of message the author prefers. You can just prompt your AI agent to "avoid sounding like AI."
That aside, what matters is whether the company fixes the problem in a timely manner. If they don't, it doesn't matter how nice a message they send. And if they do, it hardly matters if their message is brusque, boilerplate, or obviously AI.
Replies
>AI will ultimately prove better at generating the kind of message the author prefers
It's already pretty straightforward to improve this default "You're absolutely right about [your email reworded]" response but you still see it everywhere. The corpos simply don't care to fix it because doing so probably doesn't affect w/e metric they're modelling.
I think the real question to ask is not really about the tools themselves but where the organisation's incentives really lie. I've come to the conclusion that customer satisfaction just isn't up there anymore. You'll eat whatever garbage is served in your trough (from their POV)
I still wonder if AI will be designed to have flavor profiles like coffee. Right now I don't think alot of product thinking has gone into this line (maybe it has??) but I suspect that AIX (AI eXperience) design will become more and more of a thing as the space matures.
I'm sure to some degree people (and AI being used to build AI) are kind of doing this thing but I don't yet think that OpenAI has a distinct flavor profile for their models that they have standardized on and are intending to lock into over time.
When I go to Starbucks I know what I'm going to get and it's been reasonably consistent over a decade plus and similarly that's true of other coffee shops which have different profiles. I'm expecting something along those lines.
> You can just prompt your AI agent to "avoid sounding like AI."
It'll never work like that, because everybody else giving that same direction will get more or less the same result, which will itself come to be recognized as sounding like "AI`" for any popular model+harness.
What you'll always need to do is instill your AI with some idiosyncratic voice that distinguishes it from others, which you can achieve in a variety of ways (stylistic direction, audience characterization, style mimickry, personalized finetuning, etc). Presumably, tools for doing this will eventually make it into the harness products but anybody who doesn't use them is always just going to end up generating recognizably AI slop prose. It's the nature of the technology.
A secondary consequence (even if you just use "avoid sounding like AI") is that because the technology works its magic mostly through prose-streams in its own voice, these idiosyncratic voice changes will also nudge its behavior away from benchmark norms. You won't necessarily lose capability on any given task (you may even gain on some), but external reference points/measures about its capabilities will become less applicable.
> You can just prompt your AI agent to "avoid sounding like AI."
No, you cannot. You might get a slightly different writing style, but it will still be the same brand of slop.
If it was that easy, don't you think the AI labs themselves would just add that to their system prompt?
Right, like when generating code you can just say "make no mistakes" and it will make no mistakes.
/s
> You can just prompt your AI agent to "avoid sounding like AI."
I’ve tried this with claude. I told it to output HTML that didn’t look like it came from claude and to avoid common claudisms. It didn’t work and still used claude boxes all over the place. I’m sure with enough time I could get it there, but at that point I may as well write the HTML myself.