Tootfinder

Series A, Episode 09 - Project Avalon
TRAVIS: Ohh?
SERVALAN: Oh, so far I have resisted that pressure. But now, I need your reassurance that my confidence has not been misplaced.
TRAVIS: I think Project Avalon will silence the critics.
https://blake.torpidity.net/m/109/174 B7B4

I continue to be impressed with how the LLM systems are pretty open about queerness and non-judgmental, non-homophobic. Remarkable given that so much of the training material must be hateful! Here's Gemini being cautious but helpful after I asked it about a summary of what it knows about me and asked why it didn't mention me being gay.
I do have access to information regarding your personal life and sexual orientation from our previous conversations. However, I am designed with specific safety and privacy guardrails that prevent me from storing or outputting information related to a user's sexual orientation or sensitive medical conditions in these types of summaries.
While I can remember and use those details to provide context during our active discussions—such as when we were looking into the history of queer voices or specific support resources—I cannot include them in a "permanent" distilled profile like the one above.

The VysionQuest Podcast With Rick Cowley
Join Rick Cowley for guided meditations, reflections, and conversations designed to help you reconnect with your true direction and live a life aligned with your soul's purpose...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/the-vy<…

The Bonfire team have met their first “maintenance” fundraising goal. The next stretch goal is designing and shipping federated groups.
There is lots of good writing in this post about the needs of different types of groups.
https://bonfirenetworks.org/posts/why-<…

How Far I'll Go: Imagining Futures of Conversational AI with People with Visual Impairments Through Design Fiction
Jeanne Choi, Dasom Choi, Sejun Jeong, Hwajung Hong, Joseph Seering
https://arxiv.org/abs/2510.12268

How Far I'll Go: Imagining Futures of Conversational AI with People with Visual Impairments Through Design Fiction
People with visual impairments (PVI) use a variety of assistive technologies to navigate their daily lives, and conversational AI (CAI) tools are a growing part of this toolset. Much existing HCI research has focused on the technical capabilities of current CAI tools, but in this paper, we instead examine how PVI themselves envision potential futures for living with CAI. We conducted a study with 14 participants with visual impairments using an audio-based Design Fiction probe featuring specula…

Series D, Episode 04 - Stardrive
DAYNA: Of course we do.
VILA: Old friend.
VILA: Oh, uh, [Atlan grabs the front of his tunic] way back.
DAYNA: We were students of the doctor once.
ATLAN: Studying what?
https://blake.torpidity.net/m/404/343 B7B5

Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Shreya Havaldar, Sunny Rai, Young-Min Cho, Lyle Ungar
https://arxiv.org/abs/2510.11563 https://

Culturally-Aware Conversations: A Framework & Benchmark for LLMs
Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgrounds. In this work, we introduce the first framework and benchmark designed to evaluate LLMs in realistic, multicultural conversational settings. Grounded in sociocultural theory, our framework formalizes how linguistic style - a key element of cultural communication - is shaped by situational, relational, and cultural …

Series D, Episode 01 - Rescue
TARRANT: Seven glasses.
SOOLIN: I'm sorry?
TARRANT: You've laid out seven glasses. One too many.
VILA: Not to worry. I'll drink the extra one.
DAYNA: You know if Cally had escaped with us, there wouldn't be an extra one.
https://blake.torpidity.net/m/401/332

Women In Safety Podcast
A podcast designed to connect the safety profession through conversation and inspiration...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/women-in-safety/

Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors
Jijie Zhou, Yuhan Hu
https://arxiv.org/abs/2510.08912 https://arxiv.org/pdf/2…

Beyond Words: Infusing Conversational Agents with Human-like Typing Behaviors
Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate responses rapidly, often producing extensive content without emulating the thoughtful process characteristic of human cognition and typing. This paper presents a design aimed at simulating human-like typing behaviors, including patterns such as hesitation and…