I can’t come up with any interesting intro today, so I asked Gemini for a joke about open source software. “Why did the open source software go to therapy? It had to many unresolved issues.” AI isn’t taking my job any time soon.
[article] New LLM Pre-training and Post-training Paradigms. What sorts of pre-training and post-training is available to LLMs? And how do leading open models employ (or not employ) these approaches? Great writeup.
[guide] Select a managed container runtime environment. Which type of managed compute service makes sense for your next app? This new architecture guide may help you decide.
[article] What’s Behind Elastic’s Unexpected Return to Open Source? More on this somewhat-surprising move to make Elasticsearch more open again.
[blog] What are the most common bugs in LLM-generated code? It’s good to see and digest this. And it reinforces my belief that you should know how to code before depending too heavily on these AI assisted tools.
[article] Why We Shouldn’t Romanticize Failure. Ah, maybe we shouldn’t be so quick to crave a “fail fast” and “celebrate failure” culture? It sounds like we over-estimate our resilience.
[blog] BigQuery and Anthropic’s Claude: A powerful combination for data-driven insights. There’s some nice integration here between a great LLM and a terrific analytics platform.
[article] What to Do When You Know More Than Your Boss. You should know more than your boss in many areas. This is an article about knowledge sharing.
[blog]. A retryable JUnit 5 extension for flaky tests. If you’re starting to invoke LLMs in your apps, you might want to rethink your testing strategy. Guillaume wanted retry-able tests to account for non-deterministic responses.
Want to get this update sent to you every day? Subscribe to my RSS feed or subscribe via email below:
Richard Seroter's Architecture Musings 
Leave a comment