265 karma · joined March 20, 2018
When models write both the code and the tests, they might go back and forth between the code and tests until they reach a working solution. This seems dangerous.
In addition, Alphabet has reached an agreement to sell $10 billion of stock to Berkshire Hathaway Inc. in a private placement, comprised of $5 billion in Class A Common Stock at a price of $351.81 per share and $5 billion in Class C Capital Stock at a price of $348.20 per share.
This investment by Berkshire Hathaway adds to the position it has built since Q3 2025.
I understand and agree with your point though.
Give incompetent people tokens, and they become 10x better at their incompetence.
The ROI here is so high that I don't mind using the strongest model available for the actual code review. I don't trust Sonnet and such. Just let Opus or GPT 5.5 do the whole thing and pay a bit more for less complexity.
We are a large enterprise shop with many projects being built on different machines, architectures, technologies, etc. We took the time to become decent in Gradle, and it works great for us.