Don’t know what everyone’s saying, this looks sick.

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.

I wish there was a xmedium setting for GPT 5.5

Switched from @superwhisper to @WisprFlow. Performance is great, but there’s so much spam in the app and notifications. I don’t care about any of that. I just want dictation. No other notifications or workflows.

gpt 5.4 high fast on codex behaves weirdly similar to gpt 5.4 pro extended on chatgpt today. Lots of code blocks in its explanations🤔🤔🤔

Typescript > Python

coffee first, everything else second

Hot take: Opus 4.7 is a half baked step towards a right direction.

Always choose optimism over fear

That's the future right there.

Codex needs ctrl tab to bounce between recent threads.

@fal's models on the hermes agent! game changer!!

We get so used to our coding agents that switching becomes painful. It’s almost like working with a real coworker, and the other one doesn’t quite work the way you want.

Early claude code mac app review: I don't like, there's too much ceremony.

Marcus Hutchins, the guy famous for stopping the WannaCry Ransomware, probably has the best take on Mythos doing vulnerability research

Yesterday’s Mythos announcement from Anthropic was overblown. • Sandboxing was turned off, so test didn’t show much about the real world. • Cheap open-weight models can (already) do some similar stuff • No evidence that Mythos itself is a major qualitative jump. In short, we got played. cc @tomfriedman @RonanFarrow

Anthropic ruined it for us, didn’t they?

Mythos appears to be the first class of models trained at scale on Blackwells. Then will be Vera Rubins. Pre-training isn't saturated. RL works. And there is *so much* computing coming online soon. Buckle your chin strips. It's going to be fucking wild.

This is pretty huge and a dark pattern that we’ll sadly become more common.

It's actually amazing. I can run multiple codex and claude sessions and manage them through a single chat agent. You can do things like "run /review in codex and review all uncommitted changes" and The Director will actually type and click on the Codex app.