😱 “Argh - My AI Agent deleted all my files!!!!”

When was the last time one of your co-workers deleted an important file from your desktop?

I would hope it has been a long time ago and quite possibly never.

🖥️ Even at the time we used shared computers, home directories have been separated.

There was a notion of shared folders or network folders or whatever nomenclature the system you were using. So in order to provide access to files to coworkers, you would need to take the decision first to upload it to a shared folder.

Jeff Harman in on fire - pun intended in this talk “𝗔𝗪𝗦 𝗿𝗲:𝗜𝗻𝘃𝗲𝗻𝘁 𝟮𝟬𝟮𝟱 - 𝗔𝗱𝗧𝗲𝗰𝗵 𝗜𝗻𝗻𝗼𝘃𝗮𝘁𝗶𝗼𝗻 𝘄𝗶𝘁𝗵 𝗔𝗜-𝗗𝗿𝗶𝘃𝗲𝗻 𝗗𝗲𝘃𝗲𝗹𝗼𝗽𝗺𝗲𝗻𝘁 𝗳𝗼𝗿 𝗕𝗿𝗮𝗻𝗱 𝗔𝗴𝗲𝗻𝘁𝘀 (𝗜𝗡𝗗𝟯𝟯𝟯𝟰)” [1] while explaining how AdTech teams can use AWS’s AI-Driven Development Lifecycle (AI-DLC) to build production-grade “brand agents” for advertisers in about five days instead of months.[1]

Super interesting talk for everyone in advertising to get a better understanding of not only why agents will impact your business, but also build those efficiently.

𝗪𝗵𝗮𝘁 𝗵𝗮𝗽𝗽𝗲𝗻𝗲𝗱 𝘁𝗵𝗶𝘀 𝘆𝗲𝗮𝗿 𝘄𝗶𝘁𝗵 𝘁𝗵𝗲 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗔𝗜 𝘁𝗵𝗶𝗻𝗴𝘆 𝗮𝘁 𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰? 𝗪𝗵𝗮𝘁 𝗶𝘀 𝗰𝗼𝗺𝗶𝗻𝗴 𝗻𝗲𝘅𝘁?

The week(s) after re:invent are typically the time, where a pile of very good content videos pile up at my end and I have both a hard and fun time to get through this.

Today the “𝗔𝗪𝗦 𝗿𝗲:𝗜𝗻𝘃𝗲𝗻𝘁 𝟮𝟬𝟮𝟱 - 𝗪𝗵𝗮𝘁 𝗔𝗻𝘁𝗵𝗿𝗼𝗽𝗶𝗰 𝗟𝗲𝗮𝗿𝗻𝗲𝗱 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗶𝗻 𝟮𝟬𝟮𝟱 (𝗔𝗜𝗠𝟮𝟳𝟳” ended up on the top of the pile and turned the time on the rowing machine in the gym to a fun learning experience. After all it’s a level 200 session - should be able to follow it during a casual workout, right?

🎙️ In a fantastic interview “How AI will change software engineering – with Martin Fowler” at the Pragmatic Engineer Podcast [1], Martin Fowler highlights the non-determinism introduced by Agentic AI as the big challenge for adoption. So big of a challenge that he compares it to the evolution from assembler code to higher-level programming languages.

🤔 Indeed, I see a lot of customers struggling with this non-determinism. What is correct? How do I evaluate a system? What about cascading effects in multi-agent systems?

𝗔𝗜 𝗔𝗴𝗲𝗻𝘁𝘀 𝗻𝗲𝗲𝗱 𝗹𝗮𝗽𝘁𝗼𝗽𝘀 - 𝗹𝗶𝗸𝗲 𝗵𝘂𝗺𝗮𝗻 𝘀𝘁𝘂𝗱𝗲𝗻𝘁𝘀 …

This week I had the pleasure of listening to Matt Bell’s presentation on Claude models. He covered the short but impressive history of Claude and the current state of affairs.

🎯 𝗧𝘄𝗼 𝗾𝘂𝗼𝘁𝗲𝘀 𝘀𝘁𝗼𝗼𝗱 𝗼𝘂𝘁 𝘁𝗼 𝗺𝗲:

 1️⃣ “𝗟𝗶𝗸𝗲 𝘆𝗼𝘂 𝗮𝗹𝘄𝗮𝘆𝘀 𝗴𝗶𝘃𝗲 𝘆𝗼𝘂𝗿 𝗲𝗺𝗽𝗹𝗼𝘆𝗲𝗲𝘀 𝗮 𝗹𝗮𝗽𝘁𝗼𝗽, 𝘆𝗼𝘂 𝘀𝗵𝗼𝘂𝗹𝗱 𝗴𝗶𝘃𝗲 𝗖𝗹𝗮𝘂𝗱𝗲 𝗮 𝘃𝗶𝗿𝘁𝘂𝗮𝗹 𝗺𝗮𝗰𝗵𝗶𝗻𝗲.”

 2️⃣ “𝗪𝗲’𝗿𝗲 𝗱𝗼𝗶𝗻𝗴 𝘄𝗲𝗹𝗹 𝘄𝗶𝘁𝗵 𝗺𝗼𝗱𝗲𝗹 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲, 𝗯𝘂𝘁 𝘂𝘀𝗶𝗻𝗴 𝘁𝗼𝗼𝗹𝘀 𝗮𝗻𝗱 𝗼𝘁𝗵𝗲𝗿 𝗮𝗱𝗱-𝗼𝗻𝘀 𝗯𝗿𝗶𝗻𝗴𝘀 𝗺𝘂𝗰𝗵 𝗺𝗼𝗿𝗲 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗯𝗼𝗼𝘀𝘁.”