• 10 Posts
  • 406 Comments
Joined 3 years ago
cake
Cake day: June 23rd, 2023

help-circle

  • I’m a DevOps engineer (about 15 years) and in a previous life was a software engineer (15 years before that). My employer is pushing hard on AI so I reluctantly started using Claude at times. I must say that I’m fairly impressed when it comes to relatively easy tasks. We’re a large AWS user and have developed a fairly complex in-house set of python tools that encapsulate things like Terraform and Ansible. We have about 15 or so AWS sub-accounts that span logical groupings, so our IAM configuration alone was fairly complex.

    I was able to point Claude at our IAM configuration and tell it to create a set of policies/roles to allow a host in one environment to access resources in a read-only manner across all our accounts. Since I’m not an IAM expert it would have taken me a few hours to figure out what it did in under 10 minutes. Two of my team reviewed the proposed changes and were perfectly fine with them.

    I’ve also had it write python scripts that do things like call AWS APIs, collect JSON results, and compare it to contents pulled from a git repo of configuration data.

    For relatively simple tasks like these it can be a time saver. But you still need to sanity check everything it does. I’ve seen it skip steps (like not applying IAM policies to all our accounts), and when you point it out it will apologize and fix things. But it’s that sort of failure that makes me still be wary of AI. Like why only update a subset of things and fix it only after I point it out? “All” means “all”, not “some”…

    For more complex things I’m still very reluctant to trust it. When it comes to that I may use Claude to encapsulate a few API calls, but then I’ll rely on my own expertise to add in all the really important logic.












  • Here’s a bit of trivia (I worked for a startup that Ask Jeeves acquired back in 2000 & stayed on for a few more years):

    There was a brief period of time where Ask Jeeves seriously considered getting into search for porn. They went so far as to design a French maid caricature named Mimi that was to parallel the Jeeves butler that was their brand back then. They even registered a bunch of domains like askmimi.com before finally deciding they didn’t want to risk damaging the Jeeves brand, and scratched the whole project.

    Another bit of trivia: the CEO & executives at Jeeves when they acquired us were short-sighted idiots. One of the products my startup had developed was something we called “text ads” that let people bid on popular search terms for placement of ads along with the search results we served up. It was a fully automated system that required virtually no interaction on our part, and we considered it a license to print money. It brought in a good amount of revenue for us. After Jeeves acquired us they shut our text ads down and sold the service off to another small company. The Jeeves CEO at the time infamously said “we’re in the question answering business, not the advertising business” when this was sold off.

    The company that bought it made some improvements to it then re-launched it as Google AdWords, and Google quickly eclipsed Jeeves after that.





  • Why hit them more frequently? Let Russia expend the effort to completely rebuild it and get into operation and THEN you attack again. By waiting until it’s back in operation you not only maximize the repair costs, but you also target it when it’s full of highly flammable materials. That ensures maximum destruction when you hit it again. A refinery full of oil that burns for days causes much more damage than a hunk of explosives in a drone that detonates next to an empty storage tank.




  • I have a “prosumer” internet setup at home for various reasons. It’s UniFi gear, which is highly configurable, and configs are centrally managed. They provide a pretty robust web UI to manage it all, but the configuration all resides in plain text files that you can also hand edit if you want to do anything really advanced.

    While troubleshooting an issue recently I came across a post on their support forum from somebody who had used Claude to analyze those config files and make recommendations. Since I have access to Claude through my employer I decided to give that a try. I was pleasantly surprised with the recommendations it made after it spent a few minutes analyzing my configuration.