Codetown ::: a software developer's community
The ability to Interpret image data using software is advancing fast! The two images above are captioned with program generated text. Here's an article that describes concepts and an approach to generate a caption for an image. The code is written in Python and uses TensorFlow.
How to build and train an image caption generator using a TensorFlo...
"TensorFlow™ is an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API. TensorFlow was originally developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep neural networks research, but the system is general enough to be applicable in a wide variety of other domains as well." Here's a TensorFlow tutorial.
Codetown is a social network. It's got blogs, forums, groups, personal pages and more! You might think of Codetown as a funky camper van with lots of compartments for your stuff and a great multimedia system, too! Best of all, Codetown has room for all of your friends.
Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.
Check out the Codetown Jobs group.

Google Research has proposed a training method that teaches large language models to approximate Bayesian reasoning by learning from the predictions of an optimal Bayesian system. The approach focuses on improving how models update beliefs as they receive new information during multi-step interactions.
By Daniel Dominguez
Cloudflare recently announced support for ASPA (Autonomous System Provider Authorization). The new cryptographic standard helps make Internet routing safer by verifying the path data takes across networks to reach its destination and preventing traffic from traversing unreliable or untrusted networks.
By Renato Losio
DoorDash engineers built a simulation and evaluation flywheel to test large language model customer support chatbots at scale. The system generates multi-turn synthetic conversations using historical transcripts and backend mocks, evaluates outcomes with an LLM-as-judge framework, and enables rapid iteration on prompts, context, and system design before production deployment.
By Leela Kumili
Engineers at Netflix have uncovered deep performance bottlenecks in container scaling that trace not to Kubernetes or containerd alone, but into the CPU architecture and Linux kernel itself.
By Craig Risi
Alicia Collymore discusses the critical role of cultural alignment in building high-performing engineering teams. She explains how to move beyond "vibes" by identifying specific attributes in company values and assessing them during coding challenges and system design sessions. She shares practical advice on using interview debriefs, assessment criteria, and "culture add" to drive growth.
By Alicia Collymore
© 2026 Created by Michael Levin.
Powered by
You need to be a member of Codetown to add comments!
Join Codetown