Webtagr - Technology News Summarizer

LLMs and Humans Exhibit Bias: A TTS Voice Attractiveness Ranking Experiment

2025-03-10

Last year, the author used LLMs to rank Hacker News users and discovered a bias where the models consistently favored the first user mentioned in the prompt. This year, a new experiment ranking TTS voice attractiveness revealed a similar bias in human participants, who favored voices presented on the right side of the screen. This reinforces the author's previous findings and highlights the importance of sample size and randomization when using both AI and human judgments to mitigate bias.

Has Our Respect for Complexity Vanished?

2025-01-21

This blog post explores the modern societal loss of understanding and respect for complexity. With automation and the information age, direct contact with complex systems has diminished, leading to a lack of appreciation for the intricacies of fields like agriculture and manufacturing. This lack of respect manifests in simplified approaches to complex problems in daily life and impacts education and future perspectives. The author argues that admitting 'I don't know' is a valuable trait, and respect for complexity is truly admirable.

Code Rewrites: Magic Wand vs. Iterative Improvement

2025-01-03

This article explores the pros and cons of code rewrites. Using Netscape's failure as an example, the author argues that rewriting isn't always the best approach. Instead of large-scale rewrites, maintain idealism, imagine a perfect solution (wave a magic wand), and then iteratively improve the existing code. By distinguishing between necessary and accidental complexity, identify improvement directions and continually reflect on "If I could wave a magic wand, what would I want it to be?", ultimately reaching the ideal state.