sonicdr1p (@sonicdr1p) “twitter's been flooded with "google's prompt engineering course in 10 minutes" v” — TopicDigg

twitter's been flooded with "google's prompt engineering course in 10 minutes" videos this month. every one of them is someone reading slides they skimmed an hour ago here's the person who actually wrote the paper those slides rip from. lee boonstra, google ai engineer, the whitepaper's sitting at 400k+ downloads. real talk, not a recap the part that matters if you run claude past one-off chats: same prompt, same model, different context = different output. that's not a bug you fix once, it's what silently wrecks multi-step agents when nobody's checking the reasoning trail - worth watching the real thing instead of the tenth summary - what's one prompt habit that actually fixed your claude outputs? curious what's working for people rn