My focus has been on building tools that are user friendly to both humans and agents. Here's an example of an agent performing a task for me. It's scheduling book reviews, because I have a lot of content but don't want to flood the feeds. So we can watch it use the tool and then review its work. However, this example is particularly important because it gets confused and resorts to searching the source code for how my tools work. This indicates a failure in the context engineering, or the --help flags. The tool should give enough information to the agent so that its confident in its work. #Devstr image
πŸ“š Announcing: 109 Days of Book Reviews Books are like time capsules, capturing unique perspectives and preserving them for future generations. I've been reviewing almost every book I've read since 2019. Now I'm sharing one review per dayβ€”philosophy, science, fiction, and everything in between. This is also an experiment using Plurcast, part of the SCT (Simple Composable Tools) ecosystem, to schedule and crosspost to Nostr and Mastodon
πŸ“š Book Review: Sapiens by Yuval Noah Harari This was one of the most 'historical' books I have read in a while. It starts off from the very beginning of mankind, and attempts to work its way up from pre-history all the way into the coming modern ages. Although the future (and many modern innovations) aren't entirely covered, I felt it did a good job at connecting the important historical dots. I recommend this read if you want a refresher on
The future has always been uncertain. Rapidly changing technology will only make this more apparent.
So far Plurcast has been tested on Windows. If you’d like to help test on Linux or MacOS it’s greatly appreciated. View quoted note β†’