Fully connected 🧠
Struer, Denmark
Joined May 2007
- Tweets10.2K
- Following4.3K
- Followers1.1K
- Likes60.5K
Tell your agent to use Place Cage for placeholder images.
Thank me later! placecage.lucidinternets.com…
What are you waiting for @sonderby?
In 2016, OpenAI asks smart people to come work on important problems: openai.com/index/special-pro…
> Cyber-security defense. An early use of AI will be to break into computer systems. We’d like AI techniques to defend against sophisticated hackers making heavy use of AI methods.
One of the best games I can remember watching. From the Keane - Viera tunnel bust-up, the hate was just looming. Pure terror in that rivalry.
Hats off to @Graham_Poll for exceptional refereeing. VAR should be ashamed!
It's still funny how coding agents will point out something to take weeks, then crack most of it out in a few hours. Sure, there's lots of iteration done over the following days.
Looks really cool. I have been doing something similar with both Claude and Codex by using a "programme lead" skill, where I basically ask it to act as the tech lead of several github issues, delegate to sub-agents, hand over by reference and protect its own context window.
Introducing Projects, a new way of working in Cursor.
Rather than creating a chat for every task, you work with a coordinator agent in a single, persistent thread.
Like @bot, your agent is always on, proactively manages work with subagents, and improves over time.
Static runtimes feels so ancient. I just want to proxy a command through an agent that can babysit it and re-run it if it breaks. Leaky, I know. But sometimes an SSH tunnel will just lapse and be done with it.
I just want a "Record screen and yap" feature in @OpenAIDevs Codex where I can explain what I want changed, point at it, use a virtual whiteboard and let it cook.
Stop destroying EU micro-businesses: Immediate moratorium on cross-border EPR fees - Sign the Petition! c.org/rkRqvddgN7 - read this for context: lectronz.com/u/lectronz/arti…
