Listen Top Shows Blog

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

Update: 2025-04-19

Share

Description

In this episode, I spoke with Matt Carey, founding AI engineer at StackOne, founder of AI Demo Days and member of the OpenUK AI Advisory Board.

Everyone needs a friend who works in AI to help them filter the AI news and get the signals from the noise. Matt is that friend for me!

We discussed AI agents, MCP, and the challenges of AI benchmarks, which help explain the disconnect between the benchmark results and the anecdotal experiences of AI users, such as myself.

Links from the episode:

Opening theme song:
Cheery Monday by Kevin MacLeod
Link: https://incompetech.filmmusic.io/song/3495-cheery-monday
License: http://creativecommons.org/licenses/by/4.0

Comments

In Channel

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

2025-04-1948:08

#115: Introducing LocalStack v4!

#115: Introducing LocalStack v4!

2025-04-0201:03:55

#114: Best practices for building a multi-tenant system with Khawaja Shams

#114: Best practices for building a multi-tenant system with Khawaja Shams

2025-03-1248:24

#113: Why you need Knowledge Graphs for your AI chatbot | ft. Aniket Mitra

#113: Why you need Knowledge Graphs for your AI chatbot | ft. Aniket Mitra

2025-02-0545:13

#112: Better Developer Experience for Event-Driven Architectures | ft. Alex Bouchard, co-founder of Hookdeck

#112: Better Developer Experience for Event-Driven Architectures | ft. Alex Bouchard, co-founder of Hookdeck

2025-01-2959:18

#111 - EventCatalog Revolutionizes Governance in Event-Driven Architectures | ft. David Boyne

#111 - EventCatalog Revolutionizes Governance in Event-Driven Architectures | ft. David Boyne

2025-01-1751:00

#109: Building serverless apps in PHP with Bref | ft Matthieu Napoli

#109: Building serverless apps in PHP with Bref | ft Matthieu Napoli

2024-10-2455:56

#108: Lambda on Rust with James Eastham

#108: Lambda on Rust with James Eastham

2024-09-2001:02:02

#107: How to Have a Successful Cloud Career in 2024 | ft. Andrew Brown

#107: How to Have a Successful Cloud Career in 2024 | ft. Andrew Brown

2024-08-2752:33

#106: Rust with Lambda, easy-mode Rust & future of Middy | ft. Luciano Mammino

#106: Rust with Lambda, easy-mode Rust & future of Middy | ft. Luciano Mammino

2024-08-1345:51

#105: The inception story of Cognito & secret to succeeding at AWS | ft. David Behroozi

#105: The inception story of Cognito & secret to succeeding at AWS | ft. David Behroozi

2024-07-2601:14:51

#104: Baseline, is this new serverless development framework better than Amplify?

#104: Baseline, is this new serverless development framework better than Amplify?

2024-07-1657:49

#103 - Community building, being an enable, is serverless dead? ft. Allen Helton

#103 - Community building, being an enable, is serverless dead? ft. Allen Helton

2024-07-0101:00:27

#102: Building AWS communities with Farrah Campbell

#102: Building AWS communities with Farrah Campbell

2024-05-1544:05

#101: Faster serverless APIs with Brian LeRoux

#101: Faster serverless APIs with Brian LeRoux

2024-04-2301:00:19

#100: LocalStack v3 is here and it's kinda amazing!

#100: LocalStack v3 is here and it's kinda amazing!

2024-04-0201:10:00

#99: Azure Functions deep dive with Ian Griffiths

#99: Azure Functions deep dive with Ian Griffiths

2024-03-2754:03

#98: How DAZN streams live sports to millions of concurrent viewers

#98: How DAZN streams live sports to millions of concurrent viewers

2024-03-1353:06

#97: 10x Lambda cold start performance with LLRT

#97: 10x Lambda cold start performance with LLRT

2024-02-2852:55

#96: How Fathom saved $100k/year in their AWS bill

#96: How Fathom saved $100k/year in their AWS bill

2024-02-2159:33

00:00

00:00

1.0x

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

#116: AI Agents, MCP and the problems with AI benchmarks | ft. Matt Carey

Yan Cui