openai has been making it harder and harder to monitor agents.
first dots and codex cloud, where you basically can't see anything. now astra barely shows reasoning summaries at all, all while running 200 tool calls
salesforce's authorization and integration flow is the most developer-hostile shit i've ever touched, and every step somehow makes it worse. people complain about ai slop? i'd take ai slop over this bad-trip-inducing nightmare every fucking day
1
172
blizzards slow download servers helped me today. was going to download wow forever to be ready for thursday, but lucky for my family the download never started
150
there are few things i wish openai took from anthropic, but the ability to have and use hooks in chatgpt work is definitely one of them
9
685
after 3 failed attempts, a gun to my head, and lots of mocking, i managed to say coherent enough sentences to actually make it into a video, hope y'all like the platform!
kasper retweeted
Doing my part to criticize the security practices of the AI labs in normie media (the Washington Post)
kasper retweeted
I don't shill my startup very often, but this OpenAI / Hugging Face incident is too perfect: You should be using AI to monitor your AI agents, including reasoning summaries.
My company is called Embroidery, like the sewing thing. Shilling over.
kasper retweeted
I find that is you are going to generate a bunch of code, knowing the interfaces, structs, and functions will lead to much better outcomes.
Being the bottleneck is ok, your ideas are not that great.















