Coding agents with full automation like this require a different workflow that is almost purely conversational compared to Cursor/Windsurf/VS Code. It requires more trust in the model (but you can always keep Cursor open off to the side and verify its edits). But, once you get into the right rhythm with it, it can be _really_ powerful.
Sort of a strange article. You don't see that many people _not_ praising --dry-run (speaking of which, the author should really learn to use long options with a double dash).
I only saw the emdash in the thread link, but I do know that an iPad "wants" to turn a double dash into an emdash automatically. I have no idea how to disable that default.
Have you seen the show/read the manga? That's precisely the first tactic L uses against Light - he broadcasts that he has precise knowledge that he's somewhere in the Kanto region of Japan based on this timing. It's also mentioned in the article which you claim forgets to cover this.
I'd say minification/summarization is more like a lossy, semantic compression. This is only relevant to LLM's and doesn't really fit more classical notions of compression. Minification would definitely be a clearer term, even if compression _technically_ makes sense.
The "How we're building responsibly" section has nothing to do with acting responsibly. It should be called "Limitations" instead. Section reads LLM generated honestly.
reply