Yennie JuninTowards Data ScienceLLM vs LLM: Codenames TournamentA mini multi-agent competition among 3 different LLM agentsOct 121Oct 121
Yennie JuninTowards Data ScienceEvaluating Long Context Large Language ModelsThere is a race towards language models with longer context windows. But how good are they, and how can we know?Jul 313Jul 313
Yennie JuninTowards Data ScienceDealing with Cognitive Dissonance, the AI WayHow do language models handle conflicting instructions in its prompt?Jul 43Jul 43
Yennie JuninTowards Data ScienceGender Bias in AI (International Women’s Day Edition)A brief overview and discussion on gender bias in AIMar 84Mar 84
Yennie JuninTowards Data ScienceMeasuring AI’s Creativity with Visual Word PuzzlesHow well can AI models solve (and create) rebus puzzles?Feb 136Feb 136
Yennie JuninTowards Data Science2023 Wrapped: A Year of Sickness and HealthAnalyzing my own data to better understand my patterns of wellnessJan 233Jan 233
Yennie JuninTowards Data ScienceWho Does What Job? Occupational Roles in the Eyes of AIHow GPT models’ view on occupations evolved over timeDec 2, 20234Dec 2, 20234
Yennie JuninTowards Data ScienceLost in DALL-E 3 TranslationGenerating AI images in multiple languages leads to different resultsNov 2, 20233Nov 2, 20233
Yennie JuninTowards Data ScienceGPT-4 Can Solve Math Problems — But Not in All LanguagesA few experiments making GPT-4 solve math problems in 16 different languagesOct 11, 20233Oct 11, 20233
Yennie JuninTowards Data ScienceWhere Are All the Women?Exploring large language models’ biases in historical knowledgeJul 26, 202311Jul 26, 202311
