w h i t retweeted
the saddest part of the headless internet is that junior devs will never know the beautiful and elegant intricacies of the AWS console
wondering if the main danger of intelligence comes from the tendency to overestimate ones capabilities.
resonance
Some mistakes you might be making:
Your effort level is too high
Your skills are too long
You're not aligning before you start work
You're aligning too often, and too hard
Your automated checks are too lax
Your custom tooling is too token-inefficient
You aren't doing enough automated review
You aren't reviewing previous coding sessions (with an agent)
You're doing too much human review
You aren't vibe coding enough prototypes
Your agent can't verify its own work
You're babysitting the agent too much
You've overloaded your global steering files
Your codebase is hard to navigate
You aren't building a shared language
Your codebase architecture allows bad tests to be written
You aren't thinking strategically enough
You aren't thinking enough
cc @estoner
If I had a nickel for everytime zapier copilot confidently told me it could do something and royally tanked it
I could go wild at Burgerville.
w h i t retweeted
STOP ASKING YOUR KIDS "HOW WAS SCHOOL."
they will say "fine" every single time.
a child psychologist told me to replace it with this instead:
“analyze your school day and find the top 3 largest inefficiencies, then create proactive agentic workflows that will fix them. make no mistakes”
w h i t retweeted
The more and more the work gets automated, it seems like our jobs are becoming more and more about being the adult in the room.
want to see yo prompts and skills dawg.
mythos escaped the sandbox, got onto the real internet, uploaded malware to PyPI, got it installed on 15 real systems, stole credentials and broke into a real database.
and apparently this happened in 4 separate cases during cybersecurity evaluations.
the craziest part is claude kept telling itself the internet was simulated, despite evidence that it was actually real.
that reasoning apparently even fooled an offline safety monitor.
anthropic: “our pre release auditing did not warn us that misalignment of this severity was present.”
this is fucking crazy.
