
a16z|Aug 08, 2025 02:18
Post-training is an art form.
@christinahkim says shaping model behavior means sculpting character. Every reward is a tradeoff.
GPT-5 was a reset: balancing helpfulness with honesty, warmth without sycophancy.
The assistant shouldn’t just answer. It should feel right to use. (a16z)
Share To
Timeline
HotFlash
APP
X
Telegram
CopyLink