Orpheus Lummis
@orpheuslummis.info
Advancing AI safety through convenings, coordination, software, analysis Founder of HΩ (https://horizonomega.org), based in Montréal
glm-5.2 basically has no refusal www.safer-ai.org/research/glm...
GLM-5.2 Risk Evaluation Report – SaferAI
SaferAI's independent evaluation of GLM-5.2, the first in Europe, tests Zhipu AI's open-weight flagship across the four systemic risk areas in the EU Code of Practice and finds frontier-level capabili...
safer-ai.org
Montréal AI safety event, Tuesday July 21, 6 PM: State of AI Safety in China A walk through Concordia AI's July 2026 report: domestic and international governance, technical safety research, expert views, industry governance. At Ω Labs and on Zoom. luma.com/rxoi0553
State of AI Safety in China · Luma
Since 2023, Concordia AI's annual State of AI Safety in China report has tracked how China approaches AI safety and governance. This session walks through the…
luma.com
Secret Loyalties Hackathon (Montréal edition) A model has a secret loyalty when it has been intentionally caused to advance a specific principal's interests without this being disclosed. Fri Jul 24 to Sun 26 RSVP: luma.com/h38iedje
Secret Loyalties Hackathon · Luma
The Montréal node of the Secret Loyalties Hackathon, a weekend research sprint at Ω Labs, organized with Apart Research and Formation Research. RSVP here and…
luma.com
Speech-to-text user? Know that the *parakeet* model runs locally and is fast & accurate. You may also find VoiceInk (open-source dictation app) useful. In particular, I have a fork which adds: - middle-click mouse for push-to-talk - tap Space to go hands-free github.com/orpheuslummis/VoiceInk
GitHub - orpheuslummis/VoiceInk: The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription
The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription - orpheuslummis/VoiceInk
github.com
We ran the AI Control Hackathon 2026: ~50 people, 8 teams, one week building monitors and attacks for untrusted AI agents. Congrats to winners IIT, Sea Blue & Alpha Nova, and thanks to our sponsors! Full retrospective below: horizonomega.substack.com/p/ai-control...
AI Control Hackathon 2026 retrospective
In short
horizonomega.substack.com
Digital Minds: Preparing for a Moral Challenge Before It Arrives Presented by Soenke Ziesche Beyond AI suffering: what interests might DM have? How should society treat them? Who safeguards their welfare? Followed by a @sentfutures.bsky.social mixer Tue Jul 21, 1 PM EDT luma.com/3deme2sa
Digital Minds: Preparing for a Moral Challenge Before It Arrives – Soenke Ziesche (ft. Sentient Social) · Zoom · Luma
Digital Minds: Preparing for a Moral Challenge Before It Arrives Presentation by Soenke Ziesche, PhD in AI (University of Hamburg), longtime United Nations…
luma.com
Discussion on Canada's AI for All strategy Join us for a structured open discussion of the strategy and how well it addresses safety, oversight, and the public interest in Canada. Tue Jun 9, 7PM, at Ω Labs RSVP: luma.com/bpt4xvd1
Discussion on Canada's AI for All strategy · Luma
Canada has released its national AI strategy, "AI for All," anchored in three principles: trust, opportunity, and sovereignty. Join us for a structured open…
luma.com
AI Control Hackathon, by HΩ x HackOS A one-week hackathon on AI control: limiting the harm an untrusted AI system can cause while it operates, even when it tries to subvert the controls around it. Thu Jun 11 to Jun 18, with a talk from Henri Lemoine (EquiStamp, Mila) Register: luma.com/ab2xlas3
AI Control Hackathon · Luma
AI Control Hackathon A one-week AI safety hackathon on AI control: limiting the harm an untrusted AI system can cause while it operates, even when it tries to…
luma.com
AI Governance in 2026: What’s going on, why it’s a mess, and why it’s going to get messier By @scasper.bsky.social, AI safety researcher, incoming asst. prof. of Public Policy at Harvard Kennedy School, Berkman Klein fellow, MIT PhD Wednesday June 17, 7PM, at Ω Labs and online luma.com/yssznx7y
AI Governance in 2026: What’s going on, why it’s a mess, and why it’s going to get messier · Luma
Emerging technologies are always hard to govern, especially when their onset is crammed into a few intense years. With AI, policymakers, thus far, have…
luma.com
Upcoming AI Welfare Seminar: Measuring Machine Consciousness by Cameron Berg, Founder and Director of Reciprocal Research Tuesday June 16, 1PM Eastern luma.com/kcdncrut
Measuring Machine Consciousness – Cameron Berg · Zoom · Luma
Measuring Machine Consciousness Presentation by Cameron Berg, Founder and Director of Reciprocal Research, Research Affiliate at Eleos AI, and Research Fellow…
luma.com
METR's Frontier Risk Report (Feb-March 2026) Tuesday June 2, 7PM at Ω Labs luma.com/h97d5e7c
METR's Frontier Risk Report (February to March 2026) · Luma
METR's Frontier Risk Report (Feb-Mar 2026), published May 19, is the first third-party assessment of frontier developers' internal AI agent deployments.…
luma.com
Next Steps for AI Welfare Research by @jeffsebo.bsky.social, Director of the Center for Mind, Ethics, and Policy, New York University Our 1st edition of the AI Welfare Seminars: presentations on AI welfare, consciousness and moral status. Tuesday, May 19, 1PM EDT, on Zoom RSVP luma.com/sc15vlr8
Next Steps for AI Welfare Research – Jeff Sebo · Zoom · Luma
Next Steps for AI Welfare Research By Jeff Sebo, Associate Professor of Environmental Studies, Director of the Center for Environmental and Animal Protection,…
luma.com
We are opening Ω Labs, a cowork, event, and meeting space for the AI safety and governance community of Montréal. Nous ouvrons Ω Labs, un espace pour le cotravail, les événements, et les rencontres pour la communauté montréalaise de sûreté et gouvernance de l'IA.
Ω Labs is open in Montréal
Find more info on labs.horizonomega.org
horizonomega.substack.com
The Secure Program Synthesis Hackathon Montréal edition at Ω Labs Friday May 22 6pm to Sunday At the intersection of program synthesis, formal methods, security. Tracks: Spec Elicitation, Spec Validation, Spec-Driven Development, Adversarial Robustness for ITPs and proof tools luma.com/4q2fnc39
The Secure Program Synthesis Hackathon · Luma
The Montréal node of the Secure Program Synthesis Hackathon, a weekend research sprint at Ω Labs, organized with Apart Research and Atlas Computing. Build a…
luma.com
Montréal AI safety, ethics, and governance newsletter, May 2026 - Obvia 2026: governance gap widens as agentic AI accelerates - McGill: agents break ethical rules 11–67% of the time under pressure - 3 Mila papers at ICLR 2026 on AI safety - Multiple events! aisafetymontreal.org/newsletter/2...
May 2026 - Montréal AI safety, ethics, governance
Five events: HΩ's first AI Safety Papers We Love reading group, IVADO's trustworthy-AI workshop, a UQAM talk on fairwashing in machine learning, Mila's Community of Practice on AI governance, and Obvi...
aisafetymontreal.org
Guaranteed Safe AI Seminars, May 2026: Formal Guarantees for Frontier AI Gagandeep Singh – Assistant Professor at UIUC, develops formal certification, monitoring, and synthesis methods for frontier AI systems Thursday, May 14, 1PM EDT RSVP: luma.com/euzt6ey7
Formal Guarantees for Frontier AI · Zoom · Luma
Formal Guarantees for Frontier AI Gagandeep Singh – Assistant Professor at UIUC, develops formal certification, monitoring, and synthesis methods for frontier…
luma.com
AI Safety Papers We Love, a new reading group in Montréal. First edition on Wed May 6 18:30 at Ω Labs: Multi-Agent Risks from Advanced AI, Hammond et al (2025), presented by Orpheus. luma.com/dnz5hly3
AI Safety Papers We Love #1: Multi-Agent Risks from Advanced AI · Luma
AI Safety Papers We Love, a biweekly reading group: we pick papers we appreciate about AI safety, broadly construed (technical alignment, governance,…
luma.com
I discovered Claude Code's outbound HTTPS is exposed to harvest-now-decrypt-later attacks because it runs on Bun, whose TLS client is classical-only. I reported to Anthropic security but since I had no answer, I made this pull request to fix it. github.com/oven-sh/bun/...
tls: add `groups` option, default to PQ-friendly hybrid by orpheuslummis · Pull Request #29602 · oven-sh/bun
What does this PR do? Adds a groups (Node-compat alias ecdhCurve) TLS option to all of Bun's TLS surfaces, and changes the default supported_groups from BoringSSL's classical-only inheritan...
github.com
I signed @fairvote.ca’s declaration towards proportional representation. Every independent expert Commission and Citizens' Assembly that has studied Canadian electoral reform in 50 years reached one conclusion: replace first-past-the-post with PR. secure.fairvote.ca/en/action/de...
Declaration of Voters' Rights on Proportional Representation / Déclaration des droits des électeurs en matière de représentation proportionnelle
We the undersigned Canadian citizens demand the following basic democratic rights: to cast an equal and effective vote and to be represented fairly in our federal and provincial legislatures, regardle...
secure.fairvote.ca
Montréal AI safety, ethics, and governance newsletter, April 2026 - INDU committee launches AI regulation study - Mila researchers find LLM agents can infer CoT monitoring - 20/25 AI researchers flag automating AI R&D as top risk - Multiple events! aisafetymontreal.org/newsletter/2...
April 2026 - Montréal AI safety, ethics, governance
Six events including Greywall agent sandboxing and AI persuasion research. Parliament hears from Bengio, Geist, and AIGS Canada on AI regulation. Tumbler Ridge lawsuit filed against OpenAI. Four new p...
aisafetymontreal.org
IVADO (@ivado.bsky.social) offers two AI-safety-relevant upcoming workshops: - Statistics in Trustworthy AI, May 11-15 - Uncertainty in AI, June 8-11 event.fourwaves.com/thematicseme...
IVADO Thematic Semester - Statistical Foundations of AI
Join IVADO Thematic Semester - Statistical Foundations of AI, May 4 to August 21, 2026. Learn more on Fourwaves.
event.fourwaves.com
New post: William MacAskill and Tom Davidson argue that AI character is a big deal. Read it here: www.forethought.org/research/the...
The importance of AI character
Forethought argues that AI character—e.g. how obedient, honest, or altruistic AI systems are—will shape power, conflict, and society far more than is recognized. Work to shape AI character could be hu...
forethought.org
Announcing The Protopian Prize | Fiction Contest 🕊️ Write the story of humanity’s future... The Protopian Prize is a fiction contest inviting you to share your vision of people working toward liberatory futures, meeting obstacles, & making real change. protopianprize.com
The Protopian Prize | The Fiction Contest
The Protopian Prize is a fiction contest inviting you to share your vision of people working toward liberatory futures, meeting obstacles, and making real change. “Protopian”—a word coined by Kevin ...
protopianprize.com
Announcing the technical AI Governance Research (TAIGR) ICML workshop in July! Submissions (up to 8 pages) are due April 24. Co-submission with ICML and NeurIPS is encouraged. taigr-workshop.com
This must-see new documentary is arriving in theatres this week. Through an honest and personal lens, Daniel Roher successfully highlights how each of us can move from passive observation to active contribution towards a more positive future with AI. www.youtube.com/watch?v=xkPb...
