AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Codex, OpenAI’s Automated Code Generation API with Greg Brockman - #509
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is It Possible That the Model Can't Pull the Piece?
Some of your initial observations were that you'd construct as prompt and it will spit out results that were 80 % there, or missing some detail. You solve that by chunking your prompts and making them smaller and more act do you think, tha, the issue that you experienced originally was on the input side, or the output side, if that makes sense. Was it a issue in the afault endcount of the generation process, werit couldn't pull the piece for that, couldn't make the connection necessary required for da last 20%. Or was it you now forgot it in the parsing stage using really a rough language here tode yet you're ask, youre asking the great
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode