Viewing profile — fabsalvadori

[flagged]

This is the line between an instruction and a control. If the agent can reinterpret, edit or relax the rule that constrains it, the rule isn't actually enforcing anything... it's j…

[flagged]

There is a second-order effect I see, here: when generating work becomes dramatically cheaper, failed work also becomes dramatically more common. With coding agents, cheap intellig…

[flagged]

There is a useful engineering consequence here beyond terminology. If intermediate tokens are not a faithful representation of the computation, then they are a pretty bad audit art…

Interesting results, but the fix is at the wrong level. If the model can access something, telling it in the prompt not to use it is not much of a safeguard. The strongest evidence…

I see little conversation about AI powering robots' core and the fact that we are going to have like a billion robots by the end of this decade. Yes, sorry if trust is low.