zlacker

35–44. Same thing, sometimes it makes planning errors, or misses context that should be obvious based on the files, but overall a huge booster. No need to review in depth, just set it against tests and let it iterate. So much potential, so exciting.

My feeling is the current suite of LLMs are "not smarter than US" they simply have far greater knowledge, unlimited focus, and unconstrained energy (modulo plan/credits/quotas of course!). I can't wait for the AIs that are actually smarter than us. Exciting to see what they'll do.