(no title)
michaelteter | 12 days ago
I have had similar experiences to the author, and I’ve found that just working with a single agent in Antigravity (on the Gemini Pro subscription) is adequate. The extra perceived speed and power of multiple agents and/or Claude Code really didn’t match the output.
With a single Gemini (or sometimes switching to Claude Opus which inexplicably Google provides a generous amount of for free via AG) gives me incremental results so fast that I spend most of my time thinking about what I want (answering unplanned product questions or deciding how to handle edge cases).
I’m fact, sometimes I just get exhausted with so much decision making. However, that’s what it takes to build something useful; we just aren’t accustomed to iterating so fast!
HarHarVeryFunny|12 days ago
echelon|12 days ago
This is the future.
I don't think we'll ever manually write code again. It's just so much faster.
lelanthran|12 days ago
If velocity was the most important criteria, well, we could always write tech-debt faster, we just chose not to.
Unless the LLM/agent is carefully curated, it will produce tech-debt faster than it can fix it.
For some products, it seems not a problem - you just want to validate PMF on a product (of course you'll have a new problem now, which is that everyone with $20 to spare can do the same).
For others, a longer-life product is preferable. We shall have to see how things shake out. My best guess would be that we have more useless stuff that is free or close to free, and fewer useful stuff that is free or close to free.
ath3nd|12 days ago
NFTs and crypto were also the future.
> I don't think we'll ever manually write code again. It's just so much faster.
More work for the people who like to fix tech debt.