Prediction is compression

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.

To solve a problem write a program

The new ChatGPT image model is really solid. Feels much better at following fine grained direction and editing instructions.

I just chat to it, get it to ask me questions, provide responses, create keel mission, execute keel mission spoke.sh/keel/

There were signs

Paddles keeps running into spikes. I wonder if I can throw the Gemma 4 ball into the pond before Cloud Next? blog.google/innovation-and-a…

Come play my text based adventure work games. Soon questing will never be so fun... OpenAI's 2x limits come to a close tomorrow. Forever grateful of the progress it allowed me to make. I'm maxing out 2 Pro accounts, 1x Claude Max, 1x Gemini Ultra and a 1x Kimi Allegretto. If you want help setting up your own software factory or just want to talk shop about AI engineering hit me up. alexdk.com/contact

Custom local model/remote API harness Paddles (github.com/spoke-sh/paddles). Recursive context management with a different take on compaction using pressure heuristics with state space actions decided by the model first. Kimi 2.5 in the screenshot Adding support for the exciting new @PrismML 1-bit model released today!

Multi player software development is now a scheduling problem

the most magnificent data visualization ever.. literally an art piece wizard » @refikanadol

The 12-slot rule: constraint is the feature, not the bug. The heart can't overcommit. Diesel engines are governed below their ceiling. A watch face only has 12 positions. Remove the constraint and you don't get more throughput — you get shorter engine life and invisible critical paths. New post on constraint-driven prioritization → alexdk.com/blog/constraint-d…

What story are you telling?

Unix is the IDE. Especially now, in the agentic era. Every modern agent harness is just a formalized Unix control loop: command in, output out, parse, verify, repeat. The text stream was always the protocol. alexdk.com/blog/unix-is-the-…

Definitely a problem with Claude Code rate limits. I used up my 5hr session this morning way fast than normal and 20 mins after reset I've used 30? /fast mode disabled

Friday vibes. Setting sail for summer...