Adam Simpson

I do open source 📊 at @grafana. I tweet about the NBA before Christmas. I recognize cookies as currency. I love my wife, Christi. ❤s Magit.

[Adam Simpson @a_simpson]

Yesterday we launched a project in collaboration with the @okcthunder:

⚡https://t.co/3LUes7rIKT

I couldn't be more proud of how it turned out. 🏃‍♂️💨🕹

[Adam Simpson @a_simpson]

@mutewinter well played 😆

[Adam Simpson @a_simpson]

@myockey “Bash tool” calls in Pi is any interactive call. So disabling “bash” disable this whole class of problems. Of course, it’s much less useful 😅

[Adam Simpson @a_simpson]

@adamhjk Pushing on the core point idea a bit: do we even know what is core in the product?

The LLM will frame every optimization like it's essential and incredible. Maybe 1.5ms _is_ totally awesome but these decisions will compound and that's how the psychosis creeps in.

[Adam Simpson @a_simpson]

@myockey Yeah, super flexible!

[Adam Simpson @a_simpson]

Been working with Go's template library a lot recently, this slide deck (I know right?!) has been super useful https://t.co/IThe93Nozq

[BuccoCapital Bloke @buccocapital]

Levie’s Law of AI Psychosis:

The farther away you are from the actual work the more confident you are that humans are no longer needed

I like it

[Adam Simpson @a_simpson]

@mutewinter Don’t you dare paint me with that brush 🤣

[Adam Simpson @a_simpson]

@myockey @smcroasters Didn’t see it coming 😆

[Adam Simpson @a_simpson]

@mutewinter pi + gpt 5.5 is where the magic happens tbh

[Adam Simpson @a_simpson]

@badlogicgames

[Adam Simpson @a_simpson]

@myockey

[Adam Simpson @a_simpson]

Read "No Silver Bullet" today for the first time.

Highly recommend it.

https://t.co/KJbugPxTS7

[Adam Simpson @a_simpson]

https://t.co/Gn9hFWGYp0 / @badlogicgames nailed it.

[Adam Simpson @a_simpson]

I’ve started forming a strong opinion that for “agentic” security:

Custom tool definitions >>> general shell capabilities

Otherwise we’re cursed to recreate Bobby tables with new tools.

[Adam Simpson @a_simpson]

This directly applies to my other strong belief that --dangerously-skip-permissions (“yolo mode”) should be the default.

Interactive agent permissions are the productivity killer.

[Adam Simpson @a_simpson]

@mutewinter @_chenglou Nothing is stopping CoffeeScript now...

[Mitchell Hashimoto @mitchellh]

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out.

I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really).

It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely.

The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture.

We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.

I worry.

[Adam Simpson @a_simpson]

@Stammy Pretty unbeatable combo, you can always go back ;)