Loke123
Joined 7 years ago
Karma
42
Submissions
6
Member since
Apr 30
Recent submissions
Comment · 5 years ago
just to clarify - our machine is unsupervised, so it learns the normal for any application, and identifies log sequences that are novel for that application. We then turn around and feed it to GPT-3, which indeed tries to match on existing data sets in the public domain. So while the problem indeed has been documented by someone else in the world, it is still novel for that particular application.
Comment · 5 years ago
Good to hear we're not alone in thinking that this is a promising use case.
Comment · 5 years ago
:) I'm sure you're not the only one to wish that.
Comment · 5 years ago
This is a follow up to an earlier post describing the use of GPT-3 to summarize log events that describe software problems. https://news.ycombinator.com/item?id=25749820
This post shares examples of real summaries generated during beta tests, as well as examples of some sub-optimal outcomes.