gpt-6VIDEO
Sam Altman says old detailed prompts now work against GPT-6 Astra users
In a 36-minute video, Altman says Astra does in a day what used to take a team a month, and that new GPT models need less prompting, so old detailed prompting habits now backfire.
shikamaru
@shikamarutsaiArchived 2026.09.18Originally posted 2026.09.18
shikamaru @shikamarutsaiOriginally posted 2026.09.18
Sam Altman (CEO of OpenAI): "GPT-6 Astra does in a day what used to take your team a month. Most people will keep using it wrong." In 36 minutes he explains why new GPT models needs less prompting than any before, and why your old detailed ways now work against you. Watch it, then read the article below
This post quotes another post: x.com/beamnxw/status/2100486325564477856
x.com/shikamarutsai/status/2100633741744132278Archived 2026.09.18 10:08