CatOps
5.67K subscribers
94 photos
4 videos
19 files
2.25K links
DevOps and other issues by Yurii Rochniak (@grem1in) - SRE @ Preply && Maksym Vlasov (@MaxymVlasov) - Engineer @ Star. Opinions on our own.

We do not post ads including event announcements. Please, do not bother us with such requests!
Download Telegram
With the whole AI hype going on, it's interesting to see how companies are trying to find an application for AI in their products.

Sometimes it's just pure hype, in my opinion. There are some
"AI-powered" tools that existed just fine without AI. However, I personally see three major areas for AI (LLMs to be precise) in the operational field:

- Taking over some boring tasks like writing some Bash, Makefiles and so on.
- Observability: basically explaining alerts to humans and suggest possible solutions. Perhaps, even apply those suggestions.
- Knowledge management. LLM can answer reoccurring questions instead of a support person. You can even try to teach a model based on your internal documentation and so on.

And here are some practical implementations in some of those areas:

- GitLab’s new security feature uses AI to explain vulnerabilities to developers
- Pulumi AI that writes IaC for you.

P.S. The news about GitLab came from our chat. So, if you have any interesting news to share, do not hesitate to join!

#ai #gitlab #pulumi #iac
​​AI, AI everywhere…

… we could say after checking Ben Evans's presentation, where he's exploring macro and strategic trends in the tech industry for 2024.

Or we can say that it's still too early and error-prone. Or that we are not sure what we want and what possibilities it provides.

In any case, that is a good analytic, so take your time if you'd like to understand the current state of AI and its near future.

https://www.ben-evans.com/presentations

#ai