I presented the following presentation on February 27th at AI Tinkerers Atlanta. Presentation
I’m bullish on ai coding assistants, but that doesn’t come without caveats. The near term is definitely “collaboration” and “assistance”. It doesn’t make a non-developer a developer, but it can cover skill gaps related to narrow domain knowledge vs. broad understanding of why something needs to be done. Think of it like not knowing Spanish, but knowing, in English, everything you need to do to accomplish a task It’s just a chasm to cross. Seems magical, but it’s really not. ...
I’m working on a new project with workflow involving a lengthy series of LLM prompts. This got me thinking about the whole meta and layered aspects of working with these AI APIs. Including a hot take on why the chat interface is so useful for LLMs. Prompt Roundtrips = Brittle My first thought was that prompt roundtrip based workflow interactions are going to create a whole new class of brittle integrations with LLM/AI APIs. With a whole new class of error types and debugging challenges. Is the prompt wrong? Did the LLM start returning odd results? ...
In August I gave a talk at the Atlanta Go User Group related to Apache Beam processing using Go. Go is fast, but what happens when your data is larger than what a single process can handle within your available time window? Especially if you need to calculate metrics related to the data across those machines. That’s where Golang, Apache Beam and Dataflow come in. Apache Beam is an open source, unified model for defining both batch and streaming data-parallel processing pipelines. https://beam.apache.org/get-started/beam-overview/ Dataflow is a unified stream and batch data processing service on GCP that’s serverless, fast, and cost-effective. https://cloud.google.com/dataflow ...