I really like your approach on this matter. As someone who is interested in health tech, the focus on energy-bounded constraints (e.g., battery, torque) mirrors real-world healthcare resource limitations, offering foundational insights for future safety protocols in multi-agent medical systems. Well-executed.

This is a great initiative. This work provides a valuable framework for testing auditing robustness against strategically evasive model behaviors.

I think that the red-team approach can also directly address systemic risks in health AI systems where models might conceal unsafe behaviors while maintaining operational functionality which is a critical consideration for real-world clinical safety.

This is brilliant work, exactly the kind of practical, human-centered safety testing we need in health tech too. Your paired-scenario approach (unsafe vs. safe lookalikes) mirrors how we balance clinical efficiency with patient risk in AI-driven care.

By pinpointing where AI oversteps without becoming over-cautious, you’re building the trust infrastructure we desperately need for safe, useful AI systems. Keep pushing this frontier, every safe payment decision is a step toward healthier, more resilient systems.

Love the reel and the idea! This project has great potential, hope it reaches its funding goal. Good luck, John and team :)

Glad to answer any questions - today's decission to shut down Fable 5, shows that a general, non-agnostic, governance layer will be needed quite soon. It highlights the massive geopolitical and operational vulnerabilities of relying purely on centralized, platform-native AI governance.

@riyaneel I don't understand your answer. What are "strict geometric thresholds"? What conditions?

In order for you to know if it's worth your time to respond, I'll say that conditional on me knowing how it contributes to AI safety, there is around 5% of chance that I'm going to donate $1000 (otherwise, the chance is 0).

What progress have you made since your last update?

We have completed a screening of over 20 single, dual, and quad expression systems in two cell lines. We have identified several potential candidates for further study.

What are your next steps?

Work is currently being written up for publication.

Is there anything others could help you with?

Not at this time. After publication, this project will be closed and we will pursue further funding from federal and private grantmaking organizations.

Update: Proposal Concluded & Withdrawn

​The technical and computational bottlenecks outlined in this pitch have been successfully bypassed independently. The final phase of the ISB framework—including the 5th expansion (RNA velocity kinetics)—is now fully integrated, and the SDE-PDE simulation has been scaled and executed across a mega-cohort of N=100,000 virtual subjects.

​The comprehensive final manuscript is complete, and the entire production pipeline is permanently secured open-source on Zenodo and GitHub. External funding is no longer required.

Really excited to see this project come to fruition, and its impact!

@damc4 Current safety relies on behavioral patching to suppress a model's probabilistic urge to guess. CKSM handles safety at the base architectural level. By replacing probabilities with strict geometric thresholds, the model physically cannot compute a response if the conditions aren't met. It structurally abstains. Safety becomes a mathematical consequence of the system itself rather than a post-training filter.

The previous conference was incredibly meaningful to me. It led me to make some changes to my career plans based on 1-1 conversations and the event's sessions

@lisathiergart

How does that contribute to AI safety (if at all)?

Last event was great! I made some valuable connections and had very interesting chats 🙂

This is great

@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 published independent empirical dataset measuring whether AI models hold their governance constraints under real operating conditions. The infrastructure that produces the empirical evidence the policy arguments need behind them.

Policy without evidence of model behaviour is argument. Policy with a citable published dataset is defensible.

Minimum ask is $8,000. Six months of API costs and infrastructure to keep the evaluation cadence running and complete the formal ARCS publication.

Happy to answer any questions directly.

@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.

@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 ^^.

I found all 4 reasons very compelling, especially transparency

@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 conference".

I think being quite comprehensive is important -- like, knowing that all the relevant orgs and people are included would be quite helpful. Right now there's only 1k people on there and basically no people who I would think are relevant (eg the Manifund regrantors).

https://www.longtermwiki.com/ is a thing to look at for inspiration, perhaps.

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!

I really like your approach on this matter. As someone who is interested in health tech, the focus on energy-bounded constraints (e.g., battery, torque) mirrors real-world healthcare resource limitations, offering foundational insights for future safety protocols in multi-agent medical systems. Well-executed.

This is a great initiative. This work provides a valuable framework for testing auditing robustness against strategically evasive model behaviors.

I think that the red-team approach can also directly address systemic risks in health AI systems where models might conceal unsafe behaviors while maintaining operational functionality which is a critical consideration for real-world clinical safety.

This is brilliant work, exactly the kind of practical, human-centered safety testing we need in health tech too. Your paired-scenario approach (unsafe vs. safe lookalikes) mirrors how we balance clinical efficiency with patient risk in AI-driven care.

By pinpointing where AI oversteps without becoming over-cautious, you’re building the trust infrastructure we desperately need for safe, useful AI systems. Keep pushing this frontier, every safe payment decision is a step toward healthier, more resilient systems.

Love the reel and the idea! This project has great potential, hope it reaches its funding goal. Good luck, John and team :)

Glad to answer any questions - today's decission to shut down Fable 5, shows that a general, non-agnostic, governance layer will be needed quite soon. It highlights the massive geopolitical and operational vulnerabilities of relying purely on centralized, platform-native AI governance.

@riyaneel I don't understand your answer. What are "strict geometric thresholds"? What conditions?

In order for you to know if it's worth your time to respond, I'll say that conditional on me knowing how it contributes to AI safety, there is around 5% of chance that I'm going to donate $1000 (otherwise, the chance is 0).

What progress have you made since your last update?

We have completed a screening of over 20 single, dual, and quad expression systems in two cell lines. We have identified several potential candidates for further study.

What are your next steps?

Work is currently being written up for publication.

Is there anything others could help you with?

Not at this time. After publication, this project will be closed and we will pursue further funding from federal and private grantmaking organizations.

Update: Proposal Concluded & Withdrawn

​The technical and computational bottlenecks outlined in this pitch have been successfully bypassed independently. The final phase of the ISB framework—including the 5th expansion (RNA velocity kinetics)—is now fully integrated, and the SDE-PDE simulation has been scaled and executed across a mega-cohort of N=100,000 virtual subjects.

​The comprehensive final manuscript is complete, and the entire production pipeline is permanently secured open-source on Zenodo and GitHub. External funding is no longer required.

Really excited to see this project come to fruition, and its impact!

@damc4 Current safety relies on behavioral patching to suppress a model's probabilistic urge to guess. CKSM handles safety at the base architectural level. By replacing probabilities with strict geometric thresholds, the model physically cannot compute a response if the conditions aren't met. It structurally abstains. Safety becomes a mathematical consequence of the system itself rather than a post-training filter.

The previous conference was incredibly meaningful to me. It led me to make some changes to my career plans based on 1-1 conversations and the event's sessions

@lisathiergart

How does that contribute to AI safety (if at all)?

Last event was great! I made some valuable connections and had very interesting chats 🙂

This is great

@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 published independent empirical dataset measuring whether AI models hold their governance constraints under real operating conditions. The infrastructure that produces the empirical evidence the policy arguments need behind them.

Policy without evidence of model behaviour is argument. Policy with a citable published dataset is defensible.

Minimum ask is $8,000. Six months of API costs and infrastructure to keep the evaluation cadence running and complete the formal ARCS publication.

Happy to answer any questions directly.

@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.

@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 ^^.

I found all 4 reasons very compelling, especially transparency

@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 conference".

I think being quite comprehensive is important -- like, knowing that all the relevant orgs and people are included would be quite helpful. Right now there's only 1k people on there and basically no people who I would think are relevant (eg the Manifund regrantors).

https://www.longtermwiki.com/ is a thing to look at for inspiration, perhaps.

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!