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

Allow me to get to know you, mistakes and all

sebi.io

Post reply on HN
Print view View original

31–40 of 172 posts

Re: Allow me to get to know you, mistakes and all

#31

Post by borski »

I find that AI is very useful for getting me past the 'blank page' writing block, but inevitably it writes in ways I would never, and so I end up editing it heavily. But, for me, a boy with ADHD, editing something is infinitely easier than writing it from scratch.

I think this is the opposite of how most people tend to use LLMs, and I actually think my way is the "better" way. My issue has never been the act of writing well, or clearly expressing what I mean... it has been the inertia of putting words on a page at all.

(and an LLM had nothing to do with this comment :P)

Re: Allow me to get to know you, mistakes and all

#32

Post by borski »

anal_reactor wrote: post #30

I use ChatGPT for communication. It started with "please fix typos" and now it's "write me a slack message about this and that". This is mostly an effect of the communication environment we created - taking risks is rarely rewarded, and mistakes can be very costly. Remember, you're always one misunderstood message away from being fired. Of course there are people whom I trust and I'd never offend them with AI-generat…

> Remember, you're always one misunderstood message away from being fired.

If this is true, you really want to be fired. That is a horrendous work environment, and you should quit if at all possible.

Most workplaces (any certainly any good workplace) will seek to understand, not fire you immediately.

Re: Allow me to get to know you, mistakes and all

#33

Post by pmoati »

I totally agreed with you. I'm French (nobody is perfect ^^), I'm not so fluent in english and I'm dyslexic, that why I often write my message, then I ask to Claude to translate it in english because i'm feeling I will lose the credibility of my message if there is too much mistake... But you're right, so this message is not translated by LLM :D

Re: Allow me to get to know you, mistakes and all

#34

Post by chistev »

arjie wrote: post #17

I really don't mind text filtered through an LLM per se . But I prefer high signal-to-token so to speak. The way humans talk and write means that the seemingly extraneous text they add often provides an interesting insight into the thought patterns of the person, and therefore mistakes or even pointless monologues can be interesting. This is not always true. Once there was an online reaction to short content that mad…

> The way humans talk and write means that the seemingly extraneous text they add often provides an interesting insight into the thought patterns of the person, and therefore mistakes or even pointless monologues can be interesting.

Re: Allow me to get to know you, mistakes and all

#38

Post by sutib »

eterevsky wrote: post #35

I don't often use AI to cleanup my texts, but when I do, I fully own the output. I make a conscious decision whether to leave in every AI suggestion or not. The final text _is_ what I want to say.

The point of the article is it is not what you would've said. Even though you take responsibility for the result, you were never 100% the origin.

Re: Allow me to get to know you, mistakes and all

#39

Post by anal_reactor »

borski wrote: post #32
anal_reactor wrote: post #30

I use ChatGPT for communication. It started with "please fix typos" and now it's "write me a slack message about this and that". This is mostly an effect of the communication environment we created - taking risks is rarely rewarded, and mistakes can be very costly. Remember, you're always one misunderstood message away from being fired. Of course there are people whom I trust and I'd never offend them with AI-generat…

> Remember, you're always one misunderstood message away from being fired. If this is true, you really want to be fired. That is a horrendous work environment, and you should quit if at all possible. Most workplaces (any certainly any good workplace) will seek to understand, not fire you immediately.

Blessed are those who haven't worked corproate.

Re: Allow me to get to know you, mistakes and all

#40

Post by Nashooo »

borski wrote: post #31

I find that AI is very useful for getting me past the 'blank page' writing block, but inevitably it writes in ways I would never, and so I end up editing it heavily. But, for me, a boy with ADHD, editing something is infinitely easier than writing it from scratch . I think this is the opposite of how most people tend to use LLMs, and I actually think my way is the "better" way. My issue has never been the act of writ…

You're the first articulating my exact use case with AI as well! It really helps get me in 'the zone'. I actually now dictate as well and then the AI rewrite it and then I start editing. To lower the barrier even more.
Post reply on HN