Claude code even added an auto mode so that you don't get blocked by that pesky reviewing anymore. Since then, the usual mode of asking before running a command, for instance when the thing wants to read the entire codebase looking for information only available in an online doc, is now called manual mode; the non 10x developer mode.
But isn't that just a good search engine we should have separate to a LLM at that point? Semantic search doesn't need a full blown chat not in between.
Neat! Just finished a book about spiders, that despite being sci-fi, made me appreciate them more. Children of time, for those that want to check it out.
And some do parity checks to be sure they are priced similarly across all 3rd parties. But apparently booking has an outsized influence on what discounts you can apply compared to what you advertise through booking.
Woah, that is bonkers. An I assume the mental model of what the code does in the second example is also much more limited.
Any specific thing besides the usual that you can point out that made the second example so bad due to AI tools? I want to have more concrete examples on how this fails to try to push back where I work.
Would love to hear more about why English isn't made for Latin letters