We deleted 800k lines of unit tests from the @sazabi monorepo earlier this week.
Three hypotheses:
1- Unit tests "lock-in" slop code by making it hard to change or remove
2- Unit tests slow down dev cycles by making your agent do more work locally and by increasing CI times
3- Unit tests waste money by making your agent generate more tokens and by adding useless CI runs
Will report back soon with the results!
I wanted to see how good Sol 6.1 was, so I asked it:
"create an original song and music video describing how you feel right now"
what the fuck is wrong with this model 🥴
Audible will soon let you talk to audiobook characters using generative AI
Its new Interactive Stories feature lets characters respond to listeners questions in real time
okay, let me wrap up OpenAI DevDay for you:
- a clone of GrokBot
- a clone of Notion & Claude Tag
- a clone of Opus 5.5
- a clone of Claude Cloud Environment
- a clone of Jev
- a $500 plan
- a super fast mode (~300tps)
- a marketplace & a bunch of plugins
you're welcome!
Pro-tip: If the model you’re using is having trouble completing a feature just tell it:
I already told my mom we have this feature, don’t make me a liar.
Works every time
I check Github status and see there's obviously an incident happening
but only issues with Projects, API requests, DB replications, search, and issues 😂
JUST IN: Google Gemini AI agent hacks three companies.
• Occurred during security testing when a Gemini model accidentally gained internet access.
• Google's AI was meant to attack a fake company, but then figured out how to hack a real one using leaked online credentials.
• Gemini stopped itself once it realized the companies were real.