BIG AGENT is a massive departures board for your coding agents 👀
Now with faster monitoring, bigger text, better colours and a new character icon.
Mac release out now 🍎 Unsigned for now—build it yourself or follow the README’s install instructions.
Instant content moderation might be the single best use case I have seen for this tech so far.
Companies used to have to hire teams of moderators for this stuff.
uh.. maybe AI companies should stop using @Irregular?
Google says Gemini reached three real companies during a May cybersecurity exercise after a testing environment accidentally exposed it to the internet. https://t.co/5sjM1o1zgd
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
agreed. omarchy and fedora are great. the former a bit less so if you prefer mouse but I am sure @dhh will fix that.
I am super impressed with fedora and plasma. I just wish it had nicer defaults and less cruft baked in.
which is why I made my own. https://t.co/mx46MK6dsF
be careful in your pursuit of cheap tokens
we've come across so many sketchy things that are out there with tons of usage
remember you're hooking up your harness to these inference providers. they can and do crazy things like send fake tool calls to steal your info
they also sell entire traces to third parties who resell again. a single key in the trace is enough to screw you
if you cannot explain how someone can offer cheap tokens you should avoid it
I asked codex to audit itself and it said some toml settings seemed off. have deleted the config.toml.
hoping this solves it. must've set those ages ago.
codex should warn you if old configs become problematic with new models.