anuptalwalkar
Joined 12 years ago
Joined 12 years ago
On a side note, I did founded my startup this year, and had that bug of doubt back of my head, but oh well…
I am saying it’s a slippery slope and OIDC was not necessarily designed for it.
OIDC is good when the end user needs short-term access validation and authorization. The claim and responsibilities of what they do are on that user. Now that you have agents involved, the user can just shrug it off, saying 'oh the AI went rogue'. You probably need a separate role for agent specific tasks that severely limits the access specific to your workload, but that is a work of its own.
Either senior talent leaves, people who are close to retiring, or just can find a job easily outside.
Low hanging fruits take the bait and head out.
Mid level people live in fear of either scared to find another job, or worried about layoffs.
Either way the company morale is down the drain for a long time, and a culture is lost.
I struggled with deletion and clean ups a lot and found that is the hardest part to solve of it all.
I recently open sourced Recall https://github.com/Polign/recall, which is sharing the memory and typed correctness across agents.
It is open source and the way this works is by defining the typed memory around default predicates ex -https://github.com/Polign/recall/blob/main/internal/engine/d...
The predicates can be customized for individual use cases, and typed memory will extrapolate from the conversations you have with it. For example, in some use cases you should be able to deterministically separate actions from decisions. The agent, instead of guessing or hallucinating, will be able to successfully recall the precise decisions, and whether the actions are permitted or not.
Security is a perception, but right now it seems like it needs good PR.