Based on everything you know about me, roast me and don’t hold back. Make it absolutely brutal, personal, and funny. Use plenty of profanity and swear words. Leave nothing off-limits.
Send this to ChatGPT… lmk how u feel after the reply
I think we're approaching a weird era in software engineering.
Writing code is becoming the easy part.
The hard part is building an AI that can understand a massive codebase, make the right changes, test them, catch regressions, and keep going without someone babysitting it.
The IDE was the last interface.
The next one might be a goal.
chilldev retweeted
Introducing Vitals CLI
The Activity Monitor alternative that thinks in apps, not processes. Now as a command.
> brew install --cask foredotstudio/tap/vitals
$15 lifetime, only 13 left → 3 days free
👉 vitalsmac.com
chilldev retweeted
Introducing SKY-001, the first Engineering World Model.
On CAD and BIM tasks, it beats GPT-6 Astra and every frontier model we tested:
-> 51-125x faster
- > 150-210x cheaper
-> Higher IOU than all frontier models
SKY-001 lets you dream a physical object before you build it.
18 months of work. Built by the team out of Maluuba's deep learning lab (acq. by @MSRResearch).
The first ‘AI General Engineer’ will be the backbone for Autonomous Manufacturing.
chilldev retweeted
I built a Mac app that blocks your distractions and roasts you for it.
The only way back in: go outside and take a photo. Yes, it checks.
t0uchgrass.com
chilldev retweeted
new in Vitals: Claude, Cursor, and Codex limits in your menu bar.
what other AI tools should I add?
xitter.cf/attacomsian/status/211…
Vitals 1.7 is out
you find out you hit your Claude limit when Claude stops answering.
now your menu bar shows what's left, when it resets, and if you're about to run out.
works with Claude, Codex, Cursor, Grok, and more.
> vitalsmac.com
I built a Mac app that blocks your distractions and roasts you for it.
The only way back in: go outside and take a photo. Yes, it checks.
t0uchgrass.com
if i see only one more post starting with "I'm sorry Jev can what?" or something like this i'll delete my Account
chilldev retweeted
I resigned from Anthropic today. I spent the last three years doing pretraining research at both OpenAI and Anthropic. Neither company is acting responsibly. They are racing straight to self-improving superintelligence and gambling with our lives. More thoughts below.