[dead]
ai;dr
191–200 of 313 posts
Re: ai;dr
#192The correct way to use AI for writing is to ask for feedback, not the entire output. This is my personal opinion, English is not my first language, so sometimes I miss what's obvious to a native speaker. I've always used tools that tell me what's wrong with my writing as an opportunity to learn to do better next time. When I finally had Firefox on my computer and it corrected my spelling, it helped me to improve my s…
There is another correct way. Denote the general topic, ask it to ask you questions that would be needed to write it. Discard the final output, write something yourself based on what it asked.
Example (minus the final review): https://chatgpt.com/share/698e417a-4448-8011-9c29-12c9b91318...
I still think that the final review written by ChatGPT is a bit off. But at least, it asked mostly the right questions.
Re: ai;dr
#193I've been throwing in typos and shitty grammar for a while just to seem authentic. I suppose now that will be copied.
Re: ai;dr
#194> AI-generated code feels like progress and efficiency, while AI-generated articles and posts feel low-effort I've noticed that attitude a lot. Everyone thinks their use of AI is perfectly justified while the others are generating slops. In gamedev it's especially prominent - artists think generating code is perfectly ok but get acute stress response when someone suggests generating art assets.
AI-generated code is meant for the machine, or for the author/prompter. AI-generated text is typically meant for other people. I think that makes a meaningful difference.
At the same time, AI-generated code has to be correct and precise, whereas AI-generated text doesn't. There's often no 'correct solution' in AI-generated text.
Re: ai;dr
#195Earlier quoted context omitted.
My biggest sorrow right now is the fact that my beloved emdash is a major signal for AI generated content. I've been using it for decades now but these days, I almost always pause for a second.
I used to enjoy the literate usage of the word "literally". You'll get over it.
Using literally to mean figuratively goes back hundreds of years
Re: ai;dr
#196My issue is that I don't necessarily trust content if it looks generated. I think I might've lost the link, but when I was helping my company with integrating Microsoft Entra with Ubuntu, I noticed the documentation from both Microsoft & Canonical had heavily generated documentation that was flat out wrong and had me going into loops figuring out unnecessary steps that were seemingly hallucinated.
ai;dr is what I'm going to start saying, it's just frustrating to see.
Re: ai;dr
#197I've had friendships broken because people couldn't understand why I didn't appreciate their "hard work" on writing a series of 10 articles they wrote with Claude.
Mind you this person is an excellent writer, they had great success with ghost writing and running a small news website where they wrote and curated articles. But for some reason the opportunity for Claude to write stuff they can never have the time for is too great for them to ignore.
I don't care if you used AI for 99.99% of your research for writing the content but when I read your content it should be written by you. It's why I never take any article seriously on linkedin, even before AI, they all lack any personalization.
Re: ai;dr
#198I think this article overlooks the act of engaging in problem solving with an agent.
Personally I find it super helpful to discuss stuff back and forth: It takes a view, explores the code and brings some insight. I take a view and steer the analysis. And together we arrive at a conclusion.
By that point the AI’s got so much context it typically does a great job summarising the thought process for wider discussion so I can tweak and polish and share.
Re: ai;dr
#199Earlier quoted context omitted.
My biggest sorrow right now is the fact that my beloved emdash is a major signal for AI generated content. I've been using it for decades now but these days, I almost always pause for a second.
For what it's worth, whatever LLMs do extensively, they do because it's a convention in well-established writing styles. LLMs have a bias towards expertise and confidence due to the proportion of books in their training set. They also lean towards an academic writing style for the same reason. All this to say, if LLMs write like you were already writing, it means you have very good foundations. It's fine to avoid the…
I think that bias is not due to the proportion of books and more due to how they are fine-tuned after the pretraining.
Re: ai;dr
#200The author thinks that it’s fine to do this for code, which I find strange. I have big time ai:dr; when a commit comes in for me to review and it’s 300 lines for something that is already built into a single function of the framework we use, or I see a (important) comment they forgot to delete. I should not be expected to become more familiar with the authors code than he is himself, and I certainly shouldn’t be the first one verifying that even works.