Skip to main content
Original: Geoffrey Huntley · 19/07/2025

​
Summary

It might surprise some folks, but I’m incredibly cynical when it comes to AI and what is possible; yet I keep an open mind. It might surprise some folks, but I’m incredibly cynical when it comes to AI and what is possible; yet I keep an open mind. That said, two weeks ago, when I was in SFO, I discovered another thing that should not be possible. Every time I find out something that works, which should not be possible, i

​
Key Insights

“It might surprise some folks, but I’m incredibly cynical when it comes to AI and what is possible; yet I keep an open mind.” — The author shares their general skepticism towards AI’s capabilities.
“I’d been playing with eBPF and LLMs and discovered that LLMs do eBPF unusually well.” — Discussing the surprising effectiveness of LLMs in handling eBPF.
“Could we convert an eBPF trace to a fully functional application via Ralph Wiggum?” — Speculating on the potential to transform eBPF traces into applications using a tool named Ralph Wiggum.

​
Topics

​
Full Article

# this should not be possible
Author: Geoffrey Huntley
Published: 2025-07-19
Source: https://ghuntley.com/no/
It might surprise some folks, but I’m incredibly cynical when it comes to AI and what is possible; yet I keep an open mind. That said, two weeks ago, when I was in SFO, I discovered another thing that should not be possible. Every time I find out something that works, which should not be possible, it pushes me further and further, making me think that we are already in post-AGI territory. I was sitting next to a mate at a pub; it was pretty late, and we were just talking about LLM capabilities, riffing about what the modern version of Falco or any of these tools in the DFIR space looks like when combined with an LLM. You see, a couple of months ago, I’d been playing with eBPF and LLMs and discovered that LLMs do eBPF unusually well. So in the spirit of deliberate practice (see below), a laptop was brought out, and we SSH’d into a Linux machine.
deliberate intentional practice Something I’ve been wondering about for a really long time is, essentially, why do people say AI doesn’t work for them? What do they mean when they say that? From which identity are they coming from? … — Geoffrey Huntley
The idea was simple. Could we convert an eBPF trace to a fully functional application via Ralph Wiggum? So we started with a toy.

​
Key Takeaways

​
Notable Quotes

It might surprise some folks, but I’m incredibly cynical when it comes to AI and what is possible; yet I keep an open mind.
Context: The author shares their general skepticism towards AI’s capabilities.
I’d been playing with eBPF and LLMs and discovered that LLMs do eBPF unusually well.
Context: Discussing the surprising effectiveness of LLMs in handling eBPF.
Could we convert an eBPF trace to a fully functional application via Ralph Wiggum?
Context: Speculating on the potential to transform eBPF traces into applications using a tool named Ralph Wiggum.
  • [[topics/llms]]
  • [[topics/ai-agents]]
  • [[topics/deliberate-practice]]
  • [[topics/ebpf]]

deliberate intentional practice

Geoffrey Huntley · explanation · 77% similar

teleporting into the future and robbing yourself of retirement projects

Geoffrey Huntley · explanation · 74% similar

I dream about AI subagents; they whisper to me while I'm asleep

Geoffrey Huntley · explanation · 73% similar
Originally published at https://ghuntley.com/no/.