Anything else is moving the goalposts.
Anything else is moving the goalposts.
This is just wishful thinking. Anything close to real professional use, not related to IT, and closed source is king: office work, CAD, video editing, music production, and those domains immediately came to mind. Nowhere there open source can seriously challenge commercial, closed sourced competitors.
Yes, in any of those domains one can name open source products, but they are far from "winning" or "the better option".
I have emotional regulation issues. Abilify (medication), yoga, and running. Those keep me centered, reduce my (embarrassing) adult tantrums.
Social skills are the hardest part for me. I can read emotions but trying to understand people’s motivations is as complex as tracking bugs for me. It just doesn’t come naturally.
tl;dr exercise tho
Deleted Comment
I pattern match "Quests" in TFA to "projects" in GTD, and "goals" in TFA to "3-5 horizon + someday/maybe list", I don't have time to give nuanced thought to this, but I'm posting my hot take that this looks like a useful tactical method to help oneself take projects off of your someday/maybe lists and work on them, but does not fully address how to make the time.
Wait, no, it probably does, but I'm already running over my break time so I'm leaving this comment here as an anchor to come back and review after work.
We also get pretty reliable JSON output (on a smaller scale though) even without JSON mode. We usually don't use JSON mode because we often include a chain of thought part in <brainstorming> and then ask for JSON in <json> tags. With some prompt engineering, we get over 98% valid JSON in complex prompts (with long context and modestly complex JSON format). We catch the rest with json5.loads, which is only used as a fallback if json.loads fails.
4o-mini has been less reliable for us particularly with large context. The new structured output might make it possible to use mini in more situations.
Well played
Deleted Comment
Anything else is moving the goalposts.