๐จ New Podcast Launch: What if you fired your QA team and let AI write 100% of your code for six weeks?
They said it was due to "Vibe Coding." They thought they were building a unicorn at the speed of thought.
They were actually building a digital prison.
"The 42-Day Vibe" is the first ever mockumentary podcast focusing on the catastrophic failure of unsupervised automation.
S1E1: "The 42-Day Vibe - The Ghost Ledger" is LIVE.
๐ง YouTube: https://t.co/BaorqbVXcX
๐ง Spotify: https://t.co/0DZpSdET6s
Not going to spoil anything right now but you can join a closed beta waitlist from here - https://t.co/VHHMJvNQ9X
#audiophiles assemble! For a #HiResAudio experience and specifically looking for people who have high-end #iems and #dac.
I'm almost 80% there where he is now. Past month, I have seen lots of companies making this shift and being proud of shipping things quickly. We are leaning so hard into what AI can do that we are completely underestimating what we can do.
Blindly offloading everything to AI isn't how great systems are built. Yes, it'll give you a system but it probably won't be the system you actually want.
It will give you so much small wins (not denying this) that you can't see the bigger picture sometimes.
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.
Checkout the finale of the story, how did the Context Rot creep into the AI? How did they fight back?
S1E2: "The 42-Day Vibe - Final Command" is LIVE.
https://t.co/IKcTDCLR7b
๐จ New Podcast Launch: What if you fired your QA team and let AI write 100% of your code for six weeks?
They said it was due to "Vibe Coding." They thought they were building a unicorn at the speed of thought.
They were actually building a digital prison.
"The 42-Day Vibe" is the first ever mockumentary podcast focusing on the catastrophic failure of unsupervised automation.
S1E1: "The 42-Day Vibe - The Ghost Ledger" is LIVE.
๐ง YouTube: https://t.co/BaorqbVXcX
๐ง Spotify: https://t.co/0DZpSdET6s