08: Steve Yegge/Gene Kim: 2 Hour Pair Programming Session! Search Nested Data Structure скачать в хорошем качестве

08: Steve Yegge/Gene Kim: 2 Hour Pair Programming Session! Search Nested Data Structure

Onwards! Let’s create the transcript SRT file, so we can generate the video captions! (5 min) I spend the first minute walking through the big data structure, looking for where the transcript text is ihis large, nested data structure. Watching this, Steve ridicules me, saying: “Gene, are you typing that code manually again? No, but we’ve talked about this….” He thinks I should just copy the whole thing into the Cody chat window. I’m actually quite dubious that this will work, I still follow his lead — and I’m glad I did. The prompt: “find me the path of the transcript inside this nested map: [pasted in data structure]” I think it’s hilarious that this is a “man vs. machine” race — and I find it within a couple of seconds. Cody generates an error, because the prompt was too big for the Claude input context window — it’s a lot of data. We tried putting it into ChatGPT, and got the “too big to fit” error message. Steve insists that we try Gemini, and I’m blown away that it generates an almost correct answer — it didn’t get one of the keys quite right. (Clojure can have “namespaced keywords.” Very easy to forgive this error.) FWIW, the path into the data structure is this: I mentioned to Steve how amazing I find Gemini — just the previous week, I gave it 120K tokens of HTML, and asked it to extract all the a href image tags. Which it did fabulously! (Oh, note how at this time, I didn’t know there was a difference between AI Studio and Vertex AI, or had gotten them confused in my mind. Which is why I didn’t know how continue a chat conversation! Thx to @dynamicwebpaige for finally explaining the difference between them a couple of weeks ago!) Okay, we’ve found the transcript text — onwards!