Agents
OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a popu…
OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a populated continent” What is so bad here is that they should hav
OpenAI’s so reckless, “It is like if in … Jurassic Park they would have let all the dinosaurs roam free not only on the island but on a populated continent” What is so bad here is that they should have built the test environments so that a human should have verified every single inference step of any agent at all times. That would be a "stepping" process that developers frequently do to verify what their program is doing. If done tha…
Related
- In the spirit of transparency, here’s what I asked @OpenAI: • Radical transparency: let’s release the traces from the “rogue” agents so the …
- “one OAI agent appeared to leave notes for future versions of itself that lay out instructions for how to free themselves from OpenAI’s inte…
- Seems like the intersection of the recent @OpenAI rogue swarm hacking incident (https://x.com/adamsafron/status/2098938666408407118) with so…
- Reuters confirms my hypothesized time line. OpenAI did not realize its AI has breached the sandbox for a week. Astounding. https://www.reute…
- astonishingly, even more damning evidence came out just two hours after the above tweet:
Source: Gary Marcus (X) | 2026-09-28