21–30 of 155 posts
At this point, it would be shameful to not write with LLMs. I don't want to spend time reading plain human text when improved AI text is an option.
It is certainly your prerogative to believe that, but know your opinion is far from universal. It is a widespread view that AI-written text is worse.
Writing with LLMs is not a shame Or Writing with an LLM is not a shame
> Writing with an LLM is not a shame Should be "Writing with a LLM is not a shame", no reason to put a "an" here.
Is not about the letter, it's about practical pronunciation. "An r before a u, and an m or an f".
I think it's fair to use AI as an editor, to get feedback about how your ideas are packaged. It's also fair to use it as a clever dictionary, to find the right expressions, or to use correct grammar and spelling. (This post could really use a round of corrections.) But in the end, the message and the reasoning should be yours, and any facts that come from the LLM should be verified. Expecting people to read unverifie…
> message and the reasoning should be yours, I think we havent realized yet that most of us don't really have original thoughts. Even in creative industries the amount of plagiarism (or so called inspiration) is at all times high (and that's before LLMs were available).
Every time I come up with an algorithm idea, or a system idea, I'm always checking who has done it before, and I always find significant prior art.
Even for really niche things.
I think my name Aeonik Chaos might be one of the only original, never before done things. And even that was just an extension of established linguistic rules.
Just got a few recommendations by my colleagues on LinkedIn that were clearly written by an LLM, the long emdash was even present. But then again, the message was tuned to specific things I did. Also they were from Eastern Europe, so I imagine they just fixed their input. If you call yourself a writer, having tell tale LLM signs is bad. But for people who's work doesn't involve having a personal voice in written lang…
Just got a few recommendations by my colleagues on LinkedIn that were clearly written by an LLM, the long emdash was even present. But then again, the message was tuned to specific things I did. Also they were from Eastern Europe, so I imagine they just fixed their input. If you call yourself a writer, having tell tale LLM signs is bad. But for people who's work doesn't involve having a personal voice in written lang…
But LLMs are training wheels being forced on everyone, including experienced developers and we are being gaslit that if we don't use them, we are getting behind. In reality, however, the only study up to date shows 19% decline in productivity for experienced devs using LLMs.
I don't mind folks using crutches if they help them. The cognitive decline and reasoning skills of people using LLMs is not yet studied well but preliminary results show its a thing. I gotta ask: why are you guys doing that to yourselves?
I use Claude Code almost daily now, and I think I’d rather cut off my own arm than go without it, but I don’t delude myself into thinking that current gen tools don’t have significant limitations and that it is my job to manage those limitations. So just like any other tool really. I have discovered this week that Claude is really good at redteaming code (and specs, and ADRs, and test plans), much better than most hu…
Would you share with us what kind of job you do? I keep seeing people saying how amazing it is to code with these things, and I keep failing at it. I suspect that they're better at some kinds of codebases than others.
Probably. My works custom dev agent poops the bed on our front-end monorepo unless you're very careful about context, but then being careful about context is sort of the name of the game anyway...
I'm using them, mainly for scaffolding out test boilerplate (but not actual tests, most of its output there is useless) and so on, or component code structure based on how our codebase works. Basically a way more powerful templating tool I guess.