Ries: LLMs degrade actual capabilities and magnify the Dunning-Kruger effect
Eric Ries · Episode 834 | Eric Ries Revisits The Lean Startup and Discusses H... · May 26, 2026 · at 16:57
Eric Ries discusses the psychological and cognitive impacts of developers relying on LLMs for coding and work tasks.
0:00 / 0:13exact quote · 13.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“The number one biggest finding, I think, for a use of LLMs is that LLMs cause the Dunning-Kruger effect to be magnified. They convince you that you're more capable than you are at while they degrade your actual capabilities.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Eric Ries
Ries: AI in-context learning inevitably produces average work
“What they call in context learning is not learning. It's just token prediction does next token guessing. So what happens is it just, it inevitably convinces itself To do average work, because that's what's in the training data.”
Ries: Outsourcing product building to AI slows startups down
“If you just send it off to do the artifacts for you, if you have it make a product that you don't understand how that product is or what it works, if you don't talk to the customers, but you have the machine talk to customers for you, it will not actually acce…”
Ries: Vibe coding will inevitably cause a massive mission-critical disaster
“It's only a matter of time before someone vibe codes their way into a massive mission critical disaster. When they deploy code they think they understand, but they don't.”
Ries: LTSE petition caused SEC to consider ending quarterly reporting
“In fact, if you've noticed, I don't know if you've noticed the headlines in recent months that the SEC is considering eliminating quarterly reporting for the first time in 40 years. That's our petition.”