Congrats on the launch!

How are you handling cases where multiple sources of truth contradict each other?

Does Hyper assume best guess or is there any human in the loop verification?

The current conflict resolution is fairly simple: always trust humans, and trust recent human info more than old human info. We're very aware that as the knowledge system gets more complex, we'll need more sophistication, including: - Human-in-the-loop verification - Role-based ranking, i.e. be more skeptical when an intern contradicts the CEO

Unlike many other memory systems, Hyper never actually deletes memories. It constantly reranks them based on confidence, which factors into how they're retrieved. So every statement has a full history and system of record for how it got there, and you can trace (with attribution) why Hyper gives the answers it does. If there's something that Hyper misses, we provide tools in-app and in-terminal-plugin that let a human explicitly correct what Hyper knows.

The intern probably knows more about their work than the CEO in 99% of orgs. The leaf nodes who do the work know more about anything than their managers (who think they know everything but, in most organisations, understand very little). Your system must keep the managers happy to be successful, which could prove a tricky circle to square.

fair enough :) that's why it's a hard problem! different people have different levels of "trustworthiness" and this is exactly the kind of implicit mental model that employees form over years of working at a company. Hyper aims to learn these things by being an active listener, and make decisions based on that knowledge.

That is a relatively simple system. It cuts out use cases.

For instance, history, newer information is mixed with older authoritative information.

The same thing for religious institutions, where the older items may be the more authoritative for the purposes.

completing boring work is still very useful when a large proportion of peoples day jobs are managing CRUD apps

i agree, these tools are usefull. i only oppose agresive marketing that llm is solution for everything. it is just a tool which has its use case, but to me it seems that it is not optimal for use cases that it is advertised.

i work on agentic systems and they can be good if agent has a bit-sized chuck of work it needs to do. problme with the coding agents is that for every more complex thing you will need to write a big prompt which is sometimes counter productive and it seems to me that user in cursor thread is pointing in that direction.