The article mentions "human-in-the-loop" training: how does this work in practice? How much effort is required from the company's staff to train and maintain the assistant's accuracy?
(author here) This really depends on what you're trying to functionally achieve, the organisation of your knowledge base and the fidelity you're looking for.
Let's take the example of "where should the assistant look for information on topic X", the absolute minimums would be to identify possible topics & the hierarchy of places you could look.
From the product engineering POV for the build your own path, for a well defined, limited search space this should be easily doable by a single engineer in a few days to a week. As this scales out to an entire company's knowledge base this quickly becomes a quarters long project for a small ML team to build the ongoing training jobs, data pipelines & monitoring tools required to make it robust.
From the POV of users, we designed our system to give our users the option to provide as much or as little feedback as they like. We can go quite far with upvotes/downvotes on whole answers, but we also accept per reference votes & full natural language feedback. We're still working on even deeper feedback mechanisms for power users & admins but we've typically seen the vast majority of users engaging in per answer voting & then exponentially smaller groups in the more detailed mechanisms.
The discussion about AI's role in decision-making is particularly fascinating. As AI systems potentially make autonomous business decisions in the future, what checks and balances need to be in place to ensure these decisions align with a company's strategic objectives and ethical standards? How do we mitigate the risk of cascading errors from such autonomy?
Dashworks (https://dashworks.ai/) is the first and only place you need to go to find or discover knowledge about anyone or anything at work. We’re on a path to redesigning the future of collaboration and knowledge sharing. We truly have a unique opportunity to build a category-defining product (and company!) that gets used by millions every day.
We have reached a pivotal stage in our journey: we just came out of stealth, have some impressive paying customers, and are growing rapidly. Joining right now would mean you get to ride the wave of explosive top-of-the-funnel growth, yet get meaningful equity in a pre-series A startup. We’re a team of 11 and work with companies with 100-10000 employees.
As an early engineer to join our team, you'll have the opportunity to materially impact and scale not just the company's product but also the team and the culture. You'll get to drive key product initiatives end to end, and work alongside exceptionally strong co-workers who learn quickly and ship quality work.
