I’ve been running the Qwen 3.6 MoE model on my gaming laptop and have been using it to critique screenplays lately. It can’t write worth a shit, but it sure can tell me what’s wrong with my own writing.
It pointed out things like this dialog is too wordy and it ruins the joke, this story beat feels “unearned”, this character feels like a “vehicle for jokes”, this line is an “exposition dump”, etc. When I ask it for suggestions on how to fix the problems it points out, its suggestions are all stupid, but when I fix the problems myself, it no longer flags them in follow-up critiques in a new chat session.
Qwen has obviously been trained on a lot of screenplays and writing how-to books. For example, I changed the character names in a classic sitcom script, removed the series and episode title, and it recognized the writing style of the series and then even told me what episode it was. It also gives me the same advice that screenwriting books I’ve read preach, except it can point out specific cases where said principles are not being applied.
It would be better to have a human critic, of course, but finding a human who is skilled at writing and who will take the time to critique your work can be difficult. Your friends also may not give you honest feedback. Qwen will, though. It’s not sycophantic at all from what I’ve seen, and in fact, it ripped my passion project to shreds. After I fixed all the problems it found, though, it ended up being a much better piece of writing, IMO.
I think using a LLM as a tool to improve your own work instead of as a slop generator is the right way to go. I also feel better about running them on my own hardware and using about the same amount of power I’d use if playing a game instead while also retaining control of my data.
I think most creative people who openly use AI say similar things. Even with programming, I don’t ask it to code for me - I ask it to review what I wrote.
OOP is just too arrogant and ignorant to even consider this.
LLMs are a useful tool, but not a silver bullet, and if it weren’t for the shitheads overhyping them and plundering the world for profit, we’d likely not be seeing this level of backlash.
Lemmy in particular is big on self-hosting Jellyfin and the like, and running an open weight LLM on a gaming machine you already own is in the same spirit.
I have wondered if I could use AI to write unit tests, it would be worth it because it’s only a hobby project and I’m not going to do TDD otherwise. But I’m loathed to actually give the AI companies any money, especially for something that I could technically do myself, even though I won’t.
I’ve been running the Qwen 3.6 MoE model on my gaming laptop and have been using it to critique screenplays lately. It can’t write worth a shit, but it sure can tell me what’s wrong with my own writing.
It pointed out things like this dialog is too wordy and it ruins the joke, this story beat feels “unearned”, this character feels like a “vehicle for jokes”, this line is an “exposition dump”, etc. When I ask it for suggestions on how to fix the problems it points out, its suggestions are all stupid, but when I fix the problems myself, it no longer flags them in follow-up critiques in a new chat session.
Qwen has obviously been trained on a lot of screenplays and writing how-to books. For example, I changed the character names in a classic sitcom script, removed the series and episode title, and it recognized the writing style of the series and then even told me what episode it was. It also gives me the same advice that screenwriting books I’ve read preach, except it can point out specific cases where said principles are not being applied.
It would be better to have a human critic, of course, but finding a human who is skilled at writing and who will take the time to critique your work can be difficult. Your friends also may not give you honest feedback. Qwen will, though. It’s not sycophantic at all from what I’ve seen, and in fact, it ripped my passion project to shreds. After I fixed all the problems it found, though, it ended up being a much better piece of writing, IMO.
I think using a LLM as a tool to improve your own work instead of as a slop generator is the right way to go. I also feel better about running them on my own hardware and using about the same amount of power I’d use if playing a game instead while also retaining control of my data.
I think most creative people who openly use AI say similar things. Even with programming, I don’t ask it to code for me - I ask it to review what I wrote.
OOP is just too arrogant and ignorant to even consider this.
LLMs are a useful tool, but not a silver bullet, and if it weren’t for the shitheads overhyping them and plundering the world for profit, we’d likely not be seeing this level of backlash.
Lemmy in particular is big on self-hosting Jellyfin and the like, and running an open weight LLM on a gaming machine you already own is in the same spirit.
I have wondered if I could use AI to write unit tests, it would be worth it because it’s only a hobby project and I’m not going to do TDD otherwise. But I’m loathed to actually give the AI companies any money, especially for something that I could technically do myself, even though I won’t.