Amit
In the last post I described how chat interfaces to LLMs are giving a limited view of what the LLMs could do. In this post I wanted to compare this to graphics pipelines. Graphics pipelines used to be "fixed function", where the graphics system (such as Silicon Graphics hardware) would offer...
Amit
.llm-blog-post code { color: hsl(200 50% 40%); background-color: hsl(200 15% 95%); } I often see someone say "the AI said XYZ" but my understanding is that what an LLM like ChatGPT shows us is not the the LLM answering, but something slightly different. I am going to post my current...
Amit
I often put TODO comments into my projects, including in source code. And I'll change it to DONE afterwards. I ended up keeping a list of four-letter codes: This is my collection so far: IDEA: maybe someday TODO: doing later SOON: doing soon NEXT: doing now DONE: done HACK: done in a...
Amit
In online collections (photos, bookmarks, blog posts, emails, etc.), “labels” and “tags” are typically words attached to the content. For example I have a photo of a hummingbird on which I used the labels hummingbird (what it is) and coyote hills (where it was). These words are non-hierarchical,...