elliotrodriguez.me

AWS Bedrock generative AI applications that do not use provisioned throughput behind the scenes may occasionally see the following HTTP status code 500 exceptions logged in observability tools: 500 Too many connections, please wait before trying again. (Service: BedrockRuntime, Status Code: 503, Request ID: <the-id-here> You may also

One of the gaps identified early in using Bedrock was the lack of cost control and access management for on-demand inference requests. While CloudWatch records basic token utilization and latency metrics, there was little to no visibility into ad hoc requests made from the Bedrock Playground, or when using Bedrock

At AWS re:Invent, I attended a fantastic breakout session with Alessandro Cere and Matthew Monfort, where they discussed key capabilities, tools, and patterns to consider when addressing responsible AI concerns. When the topic of agents came up, I was surprised to see that little attention was given to the

Advent of Code is one of my favorite programming pastimes! According to The New Stack, this is celebrating its 9th year! In the past I've participated in the SANS Holiday Hack Challenge as well (think Project Euler, but with holiday themes). PoCs are great for keeping up in

I've recently created an account on Bluesky. While I am still not really sure how I might leverage this new service, it certainly claims to have some pretty strong adoption numbers and looks very much like the service it intends to replace (and poach users from). So I

It only dawned on me a week ago that AWS re:Invent starts on the same day the rest of the US goes collectively home from the Thanksgiving holiday. It then dawned on me that I'm flying through not just the nation's busiest airport, but the