Claude models have seriously digressed since 4.6 and in some of the most meaningful ways to pro and vibe coders alike. I'm holding onto 4.6 until the bitter end.
You're right. I just re-checked. 4.8 and 5 gave a blatantly wrong answer to a simple question, 4.6, Quen, GLM, Sol gave the right answer. They messed up somehow, not sure what they did.
You're right. I just re-checked. 4.8 and 5 gave a blatantly wrong answer to a simple question, 4.6, Quen, GLM, Sol gave the right answer. They messed up somehow, not sure what they did.