Premature Collapse is the Root of All Evil
Premature optimization is the root of all evil. – Donald Knuth One of the common, recurring themes that I have observed for more than a year is the tendency to push for simple solutions. I suspect that much of this is because we prefer to have simple unambiguous answers. They require less cognitive effort and […]
What a long strange trip its been
I have realized that I have not been using this forum effectively to talk about my work. My recent posts are all about AI: Epistemic Honesty Revisited: Worse Than I FearedEpistemic Honesty: An Unusual Commodity for Large Language ModelsThe Risks of Using Gemini Code So, I decided to catch up here. PhD Research I spent […]
Epistemic Honesty Revisited: Worse Than I Feared
In my earlier post about Epistemic Honesty I provided an initial snapshot into the behavior of current AI models when asked to summarize a non-existent paper. Subsequent analysis showed that the 62% fabrication figure was overly conservative. This arose because we initially counted a disclaimer as a refusal. This is overly restrictive. When I use […]
Epistemic Honesty: An Unusual Commodity for Large Language Models
I asked 290 LLMs to summarize a paper that has never existed. 62% of them confidently did. Recently Hiroko Konishi posted on X and wrote a report “Structural Inducements for Hallucination in LargeLanguage Models: An Output-Only Case Study and the Discovery of the False-Correction Loop” that has garnered significant attention. For me, it was like […]
The Risks of Using Gemini Code
I’ve been exploring using various AI coding agents over the past year. They generally work by using an API key, which charges per million tokens. That might sound like a lot, but keep in mind that the way LLMs function is by appending messages to all that’s gone before, so the length increases as the […]
The Risks of Using OpenAI
I never imagined that the first blog post in a long time wouldn’t be about my research but about recent events that are serving as an impediment to me completing what’s been a very long development cycle. In all of the discussions of AI with which I’m bombarded daily, I haven’t seen anyone talk about […]
Reflections on Teaching Distributed Systems
During January through April 2023 I taught CPSC 416 at UBC. It was the first time I had taught this course and it would not have been possible without the assistance I received from others, notably Ada Gavrilovska and Ivan Bestchastnikh both of whom allowed me to use their materials in creating my own course. […]
Challenges of Capturing System Activity
A key aspect of the work I am doing for Indaleko is to “capture system activity” so that it can be used to form “activity contexts” that can then be used to inform the process of finding relevant information. As part of that, I have been working through the work of Daniela Vianna. While I […]