In the year since I first wrote about AI assistance, I’ve been using LLMs increasingly for my job, personal projects, and writing. They fill several roles for me:

• a sophisticated search engine with the most flexible of query languages and arbitrarily customizable output formats;
• the ultimate rubber duck, one that quacks back statistically generated opinions;
• a fast, knowledgeable, overeager albeit sloppy junior programmer;
• an English proofreader with a bad taste.

Beyond these specific uses, I see much potential in the malleability of tool. As it continues to improve, I can see myself building more sophisticated workflows and personal applications; using voice instructions while pair programming; having agents run commands in the shell and integrating applications; building local knowledge bases from code, text, and every little note I can scribble in the margin of my editor: a second brain to query and look at from all angles.

If I filter all the noise—which is loud—and try to be objective, I admit that even in their present flawed incarnation, LLMs may well be the most powerful human augmentati