alt Hacker NewsIt's pretty amazing what you can do when you embrace LLMs, figure out how to build one high-quality rigorous project with them, and then start working on more projects.
You become a machine with your workflow, once again limited only by your time/energy, tokens, and your discretion on how to spend it.
Replies
plastic-enjoyer • yesterday at 5:10 PM
> It's pretty amazing what you can do when you embrace LLMs, figure out how to build one high-quality rigorous project with them, and then start working on more projects.
Indeed. But I think it's fair to say that just embracing LLMs is not enough.
➕ show 1 reply
bitwize • yesterday at 6:20 PM
It's 2026. Not using AI is deliberately hobbling yourself. You won't be able to produce as good code, nearly as fast.
➕ show 1 reply
matching decompilation is a verifiable target. Its hard to create slop that still matches. The same does not hold up for coding with llms normally.