Ask HN: Anyone Else Blurting?

I was initially excited about LLMs, especially on the generous free tiers, but now using them feels like a chore due to constant corrections, the need to prompt for brevity, and their grating certainty and sycophancy. I've noticed that instead of crafting precise prompts, I've started just blurting—typos, missed words, poor structure—reasoning that it will get the picture anyway or expecting it to be 15% wrong. I worry that this communication style, like typographic grunting, is making me dumber and degrading my thinking, since writing is tied to thinking. Is anyone else experiencing this?

Today I got really frustrated that even with the care I’ve taken in architecting a code base, my agents went crazy and added complexity for a scenario that made no sense. I think this tech is good but also not great, but we have to pretend it is because it isn’t bad. I don’t want to write code by hand again, but I find myself getting mad at the agent for doing something dumb. I don’t know if the agents are trying to show off or be cheeky. It is like a bike shedding nightmare. Something I wish to avoid. I’m using 6.1 sol and 5.6 on highest effort.
I do. Maybe not terribly but quite a bit. And for all the same reasons as yours :) Although this happens less frequently with Chinese models, and recently Gemini Argon with medium level thinking. Anthropic and OpenAI appear to have defined success as number of prompts sent or number of assistant responses, which means more work for me, so I am out. Plus, I wouldn’t talk to someone twice if they caveat every answer to a question and require me to follow up. I don’t ask questions expecting partial answers with exactly 1 caveat/nuance.
It's poor form. You're lifting from your back. You're throwing punches from your elbow. You shouldn't anticipate that it will get 15% off and steer. You try to get it up to 100% before writing any code, and sometimes that involves getting it to scout what's already there. Control the environment. The scope used to be code and architecture, now it's context. These models are designed to fill in gaps and propose solutions. If they don't know what you want, you have productivity in the the wrong direction. If you want somewhere to start, look into Matt Pocock's public videos and https://www.aihero.dev/ A rule of thumb would be to speak to it like a teacher would. It has always worked on all models.
No, if anything I'm probably more formal in my communications toward AI with respect to grammar and punctuation and all that, than I am in my casual digital communication with friends and coworkers.