How does that contribute to AI safety (if at all)?
Recent activity
The latest comments on organizations, projects, and funds.
The latest comments on organizations, projects, and funds.
The latest comments on organizations, projects, and funds.
How does that contribute to AI safety (if at all)?
@Jesse-Richardson this sits directly underneath the policy and preparedness work you have been funding.
183,924 evaluations across 32 models from 13 providers. The finding that matters for AGI preparedness. Every model tested accepted false authority claims at every temperature. Architectural. Temperature invariant. No intervention resolves it.
This is not a benchmark. It is the only…
Hi @Austin, I thought you might be interested to check this out: http://aisa.nahdha.tech -- I welcome feedback!
@Ahmed briefly, I think this is going in an interesting direction, but I'm not as interested in a fancy world map thing; like Ronak says, a version that's just a plain table or db (and maybe with a straightforward API or sth) would be useful to answer questions I have, which are often of the shape "who might I reach out to hire for a role at Mox" or "who should I invite to speak at this…
@Austin thanks for the feedback, it's helpful. I worked on it again: it's a directory now, just a fast searchable and filterable table of real people and orgs. Would mean a lot if you check it again. And thanks for the longtermwiki pointer, it helped.
Love the project idea, but the frontend site is extremely heavy; would appreciate a default/landing page that doesn't cause my fans to spin up :). Would be nice if there's a version that's literally just a table/database that can be searched/filtered directly or semantically.
Also highly recommend frontend projects prioritize a feedback button. :) Good luck!
@ronakrm Done a chunk of this. The default landing is a fast, lightweight table now, with direct search and filters. Feedback button is in :). Semantic search is next on the plan. please check again!
Thanks for the steer ^^.
new root comment
thread reply
reply in thread
Matt comment thread root
Matt reply test for email notif
A super cool project!
Thanks!! @aashkapatel
I use this code base, it replicates, and is a low overhead environment to study reward hacking - which means it speed up research iterations.
Search for CIRIS on google play or the app store, or go to https://ciris.ai/install
thank you @RyanKidd !!
https://saihm.coti.global/blog/2026-05-31-what-makes-saihm-different
What makes SAIHM different
2026-05-31 · SAIHM · for anyone comparing AI memory tools · ~6 min read
Ask most AI memory tools what they do and you hear the same sentence: they remember things for your AI so it does not start from scratch…
Keep up the good work ❤️
@alexs Thanks for your support!!! For Mission Partner access, DM me in the https://doomdebates.com/discord server :)
Congrats on the funding
Current papers can be found here https://zenodo.org/records/20214699
[Progress update]
The original proposal was to focus our consulting support on assisting policymakers to in the US, UK, EU, and UN working on AI Safety, providing ad hoc research, developing communication strategies, and reasoning through strategic questions during critical decision-making moments.
The aim was to increase the capacity of constrained government departments, support policy…
[Final report]
No major changes from what I wrote — this was a small one-time travel grant to allow me to go to ICML.
[Final report]
1. What Was Completed
The project produced two substantive published works:
[Progress update]
- What progress have you made since your last update?
Since the last update, we have completed the main empirical phase of the project. The work has now been written up in a paper, "Beyond Viewpoint Affinity: Measuring Political Bias in LLMs as a Failure of Epistemic Consistency," which…
[Final report]
Hey Tom, just thought you might be perfect for this short form video AI safety creators thing: https://plzdontkillus.com priority deadline is tomorrow!
SAIHM is the candidate global standard for Sovereign AI Horizontal Memory — the memory-protocol companion to the Model Context Protocol (MCP) tool layer. The campaign is multi-track and runs in parallel across every active forum.
Position: protocol layer, not implementation. SAIHM specifies the cell shape, identity binding, encryption envelope, audit anchor, sharing contract, and…
[Progress update]
We published and routed our May 12th Open Letter to President Trump:
[https://www.cbpai.org/blog-1/an-open-letter-to-president-donald-j-trump-the-ai-deal-of-the-century-is-yours-to-strike](https://www.cbpai.org/blog-1/an-open-letter-to-president-donald-j-trump-the-ai-deal-of-the-century-is-yours-to-strik…
Endorsement comment
This is a community endorsement comment
I think this project is great!
Hi! I love the idea of a programming language for AI Safety, but I have a hard time understanding your list of features. Perhaps some example code would help? Do you have some documentation, or at least a github page for your programming language? The docs don't have to be polished; I know that the documentation I wrote for my team's programming language…
live app already running using triadic alignment in base frontier models with no RLHF https://triadai.tech
I've gone to multiple https://www.tech-ish.org/ events hosted by Lauren and they were all great! Good discussion and moderation, and she consistently brings together people that would have rarely met / chatted otherwise. She clearly understands the AGI topic and can bridge the gap between technical and non-technical people in a thoughtful way.
I think this…
I’ve included one Egyptian example on the page to show how the method works in practice.
I’m now starting to gather feedback on additional cases.
If anyone is interested in reviewing a single sheet or giving quick input on the claim → evidence → result flow, I’d really value that.
The goal is not to force a decipherment claim, but to test whether AI-generated interpretations can be checked…
Tomoko-San,
I know you will impress everyone with your insights
Ganbatte Ne!
Eric
@Ericfrasersf Thanks so much Eric! I am still struglling to build the deck mainly because as you know, Japanese presentation documents have too many words while Western tend to have a few.
And Yes, ganbarimasu!
