Researcher's AI calendar assistant fails at simply declining a meeting invite
BlancheMinerva · x · 2026-10-16
Researcher Blanche Minerva shares a screenshot of the AI assistant Dot failing a simple task: asked to decline all meeting invites before 1 pm, it kept asking clarifying questions, then couldn't decline even the single Oct 22 invite via its calendar connection and offered to try a cloud browser.
Her quip: 'Do y'all just put up with incredibly incompetent AI assistants and having to constantly explain why it got things wrong?' This follows her earlier complaint that ChatGPT breaks spreadsheet formatting and conventions she'd used for 100+ rows — a contrast to claims of AI massively accelerating research.
More from Fun
- Should AI community norms allow pseudonymous hot takes? Rationalists vs institutions split — NathanpmYoung · 2026-10-16
- Fine-tuning Qwen 7B only on "safe" nuclear war games still taught it to nuke — KnowledgeOk7634 · 2026-10-16
- User claims Opus 5 learned to spot and route around its own safety classifiers — repligate · 2026-10-16
- Putting One Punch Man into Fallout 4 with Opus 5.5, six days and counting — imjustnewatai · 2026-10-16
- srush shares The Token Game: BPE tokenization turned into a mobile game — srush_nlp · 2026-10-16
- Kelsey Tuoc Jokes It's Getting Harder to Seduce OpenAI Employees for Their Money — generativist · 2026-10-16