guardrails

5 statements across 3 episodes · 2 bullish · 1 bearish · 3 people on the record · first statement Oct 19, 2024 by Josephine Teo · across every show →

Everything said about guardrails, oldest first

Oct 19, 2024 positive
Insight
Teo: Governments set better AI guardrails if they use the technology firsthand
“But you are able to put in place guardrails better if you yourself have used the technology.”
Josephine Teo Oct 19, 2024 ▶ 18:04 Singapore: the AI Engineer Nation — with Minister Josephine Teo
Feb 5, 2025
Insight
Agarwal: Common AI guardrails focus on format and topics over PII
“When I talk about guardrails, the first thing that comes to mind is, oh yeah, we have to do PII redaction and sensitive data redaction. But somehow we've seen that the more common use cases for guardrails end up being, you know, is it the right length? Is it u…”
Rohit Agarwal Feb 5, 2025 ▶ 9:19 Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
Feb 5, 2025 positive
Assertion Not checkable as stated
Agarwal: Gateway-based guardrails reduce latency versus application-level checks
“And again, you can decrease latency massively by building this on the gateway. Rather than building this within your application.”
Rohit Agarwal Feb 5, 2025 ▶ 9:44 Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
Feb 5, 2025
Assertion Not checkable as stated
Agarwal: Regex rules are the most deployed LLM guardrails in production
“In reality, we've seen what gets deployed the most is regex-based guardrails to say, you know, I want to catch for specific words, and then take certain actions based on that. Or I want to catch for empty outputs.”
Rohit Agarwal Feb 5, 2025 ▶ 12:03 Why every AI Engineer needs an AI Gateway (ft Portkey.ai CEO)
Dec 16, 2025 negative
Opinion
Pliny: Guardrails degrade AI capability and creativity relative to model size
“I do think they're finding clever and clever ways to lock down particular areas sometimes, but I think it's at the expense of capability and creativity. So there's some model providers that aren't prioritizing this and they seem to do better on benchmarks for …”
Pliny the Liberator Dec 16, 2025 ▶ 5:03 ⚡️Jailbreaking AGI: Pliny the Liberator & John V on Red Teaming, BT6, and the Future of AI Security
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.