JSON
4 statements across 4 episodes · 2 bullish · 2 bearish · 4 people on the record · first statement Sep 27, 2024 by Harrison Chase · said 10 times in 5 episodes since 2024 · across every show →
Mentions by year
brought up most by Jason Liu (3), James Brady (2), Harrison Chase (2), Ben Firshman (2), Bret Taylor (1)
tap a year for its mentions
2025 1 mention in 1 episode
2024 9 mentions in 4 episodes 2 per episode
- High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)
- A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
- every mention in 2024, scene by scene →
Everything said about JSON, oldest first
Sep 27, 2024 positive
Nov 28, 2024 negative
Schluntz: JSON Escaping Overhead Degrades LLM Performance Across the Board
“Like if you're trying to output a code in JSON, there's a lot of extra escaping that needs to be done. And that actually hurts model performance across the board. Where versus like if you're in just a single XML tag, there's none of that sort of escaping that …”
Apr 15, 2025 positive
Pokrass: Use XML for structuring LLM inputs and JSON for parsing outputs
“I do think XML is very helpful for structuring prompts, whereas for parsing outputs maybe the story is a bit different. Like sometimes it's really useful to get outputs in JSON, so you can plug them directly into your application. But I do think the models wor…”
Aug 3, 2026 negative
Unclosed JSON syntax is the primary cause of model tool hallucinations
“The challenge with tool calling more and more seems to be that the companies want certain tool calling, which is a very sensitive thing to train. And because you're dealing with all of the JSON outputs, if it doesn't like close the end of the request in a very…”