Important research project! Isaak, Helena are awesome and assembling a great team that should make progress on it
Vincent Weisser
@vincentweisser
focused on open/decentralized agi, alignment and scientific progress
vincentweisser.com$0total balance
$0charity balance
$0cash balance
$0 in pending offers
Outgoing donations
Luthien
$200
10 months ago
Luthien
$200
10 months ago
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents
$250
11 months ago
Investigating and informing the public about the trajectory of AI
$250
11 months ago
human intelligence amplification @ Berkeley Genomics Project
$100
11 months ago
Attention-Guided-RL for Human-Like LMs
$100
11 months ago
human intelligence amplification @ Berkeley Genomics Project
$500
11 months ago
AI-Driven Market Alternatives for a post-AGI world
$115
about 1 year ago
AI-Driven Market Alternatives for a post-AGI world
$100
about 1 year ago
MATS Program
$200
about 1 year ago
Lightcone Infrastructure
$100
about 1 year ago
Next Steps in Developmental Interpretability
$200
about 1 year ago
10th edition of AI Safety Camp
$200
about 1 year ago
Biosecurity bootcamp by EffiSciences
$100
about 1 year ago
SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents
$200
about 1 year ago
Investigating and informing the public about the trajectory of AI
$200
about 1 year ago
Making 52 AI Alignment Video Explainers and Podcasts
$50
almost 2 years ago
AI Safety Research Organization Incubator - Pilot Program
$200
about 2 years ago
AI Safety Research Organization Incubator - Pilot Program
$277
about 2 years ago
AI Safety Research Organization Incubator - Pilot Program
$500
about 2 years ago
Scaling Training Process Transparency
$150
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$100
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$10
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$100
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$790
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$1000
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$210
about 2 years ago
Cadenza Labs: AI Safety research group working on own interpretability agenda
$500
about 2 years ago
Exploring novel research directions in prosaic AI alignment
$200
about 2 years ago
MATS Program
$300
about 2 years ago
MATS Program
$500
about 2 years ago
Empirical research into AI consciousness and moral patienthood
$50
over 2 years ago
Empirical research into AI consciousness and moral patienthood
$70
over 2 years ago
Run five international hackathons on AI safety research
$100
over 2 years ago
Avoiding Incentives for Performative Prediction in AI
$50
over 2 years ago
AI Alignment Research Lab for Africa
$150
over 2 years ago
AI Alignment Research Lab for Africa
$100
over 2 years ago
AI Alignment Research Lab for Africa
$150
over 2 years ago
WhiteBox Research: Training Exclusively for Mechanistic Interpretability
$100
over 2 years ago
Avoiding Incentives for Performative Prediction in AI
$100
over 2 years ago
Discovering latent goals (mechanistic interpretability PhD salary)
$150
over 2 years ago
Introductory resources for Singular Learning Theory
$50
over 2 years ago
Holly Elmore organizing people for a frontier AI moratorium
$100
over 2 years ago
Recreate the cavity-preventing GMO bacteria BCS3-L1 from precursor
$50
over 2 years ago
WhiteBox Research: Training Exclusively for Mechanistic Interpretability
$150
over 2 years ago
Activation vector steering with BCI
$150
over 2 years ago
Avoiding Incentives for Performative Prediction in AI
$50
over 2 years ago
WhiteBox Research: Training Exclusively for Mechanistic Interpretability
$70
over 2 years ago
Alignment Is Hard
$70
over 2 years ago
Introductory resources for Singular Learning Theory
$70
over 2 years ago
WhiteBox Research: Training Exclusively for Mechanistic Interpretability
$100
over 2 years ago
Compute and other expenses for LLM alignment research
$100
over 2 years ago
Optimizing clinical Metagenomics and Far-UVC implementation.
$100
over 2 years ago
Apollo Research: Scale up interpretability & behavioral model evals research
$160
over 2 years ago
Apollo Research: Scale up interpretability & behavioral model evals research
$250
over 2 years ago
Run five international hackathons on AI safety research
$250
over 2 years ago
Holly Elmore organizing people for a frontier AI moratorium
$100
over 2 years ago
Discovering latent goals (mechanistic interpretability PhD salary)
$400
over 2 years ago
Discovering latent goals (mechanistic interpretability PhD salary)
$40
over 2 years ago
Scoping Developmental Interpretability
$45
over 2 years ago
Scoping Developmental Interpretability
$1000
over 2 years ago
Scoping Developmental Interpretability
$455
over 2 years ago
Joseph Bloom - Independent AI Safety Research
$250
over 2 years ago
Joseph Bloom - Independent AI Safety Research
$100
over 2 years ago
Joseph Bloom - Independent AI Safety Research
$50
over 2 years ago
Agency and (Dis)Empowerment
$250
over 2 years ago
Isaak Freeman
$100
over 2 years ago
Medical Expenses for CHAI PhD Student
$43
over 2 years ago
Long-Term Future Fund
$50
over 2 years ago
Comments
Vincent Weisser
about 2 years ago
Awesome work! One of the most exciting areas of alignment in my view!
Vincent Weisser
about 2 years ago
Very excited about this effort, think it could have great impact, and personally know Kay and think he has a good chance to deliver on this with his team!
Transactions
| For | Date | Type | Amount |
|---|---|---|---|
| Luthien | 10 months ago | project donation | 200 |
| Luthien | 10 months ago | project donation | 200 |
| Manifund Bank | 10 months ago | withdraw | 14000 |
| SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents | 11 months ago | project donation | 250 |
| Investigating and informing the public about the trajectory of AI | 11 months ago | project donation | 250 |
| human intelligence amplification @ Berkeley Genomics Project | 11 months ago | project donation | 100 |
| Attention-Guided-RL for Human-Like LMs | 11 months ago | project donation | 100 |
| human intelligence amplification @ Berkeley Genomics Project | 11 months ago | project donation | 500 |
| AI-Driven Market Alternatives for a post-AGI world | about 1 year ago | project donation | 115 |
| AI-Driven Market Alternatives for a post-AGI world | about 1 year ago | project donation | 100 |
| MATS Program | about 1 year ago | project donation | 200 |
| Lightcone Infrastructure | about 1 year ago | project donation | 100 |
| Next Steps in Developmental Interpretability | about 1 year ago | project donation | 200 |
| 10th edition of AI Safety Camp | about 1 year ago | project donation | 200 |
| Biosecurity bootcamp by EffiSciences | about 1 year ago | project donation | 100 |
| SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents | about 1 year ago | project donation | 200 |
| Investigating and informing the public about the trajectory of AI | about 1 year ago | project donation | 200 |
| Manifund Bank | about 1 year ago | deposit | +17015 |
| Making 52 AI Alignment Video Explainers and Podcasts | almost 2 years ago | project donation | 50 |
| AI Safety Research Organization Incubator - Pilot Program | about 2 years ago | project donation | 200 |
| AI Safety Research Organization Incubator - Pilot Program | about 2 years ago | project donation | 277 |
| AI Safety Research Organization Incubator - Pilot Program | about 2 years ago | project donation | 500 |
| Scaling Training Process Transparency | about 2 years ago | project donation | 150 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 100 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 10 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 100 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 790 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 1000 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 210 |
| Cadenza Labs: AI Safety research group working on own interpretability agenda | about 2 years ago | project donation | 500 |
| Manifund Bank | about 2 years ago | deposit | +500 |
| Manifund Bank | about 2 years ago | deposit | +500 |
| Manifund Bank | about 2 years ago | deposit | +1000 |
| Manifund Bank | about 2 years ago | deposit | +1000 |
| Manifund Bank | about 2 years ago | deposit | +300 |
| Exploring novel research directions in prosaic AI alignment | about 2 years ago | project donation | 200 |
| Manifund Bank | about 2 years ago | deposit | +200 |
| Manifund Bank | about 2 years ago | mana deposit | +10 |
| MATS Program | about 2 years ago | project donation | 300 |
| MATS Program | about 2 years ago | project donation | 500 |
| Manifund Bank | over 2 years ago | deposit | +500 |
| Manifund Bank | over 2 years ago | deposit | +300 |
| Empirical research into AI consciousness and moral patienthood | over 2 years ago | project donation | 50 |
| Empirical research into AI consciousness and moral patienthood | over 2 years ago | project donation | 70 |
| Run five international hackathons on AI safety research | over 2 years ago | project donation | 100 |
| Avoiding Incentives for Performative Prediction in AI | over 2 years ago | project donation | 50 |
| Manifund Bank | over 2 years ago | deposit | +200 |
| AI Alignment Research Lab for Africa | over 2 years ago | project donation | 150 |
| AI Alignment Research Lab for Africa | over 2 years ago | project donation | 100 |
| AI Alignment Research Lab for Africa | over 2 years ago | project donation | 150 |
| WhiteBox Research: Training Exclusively for Mechanistic Interpretability | over 2 years ago | project donation | 100 |
| Avoiding Incentives for Performative Prediction in AI | over 2 years ago | project donation | 100 |
| Discovering latent goals (mechanistic interpretability PhD salary) | over 2 years ago | project donation | 150 |
| Manifund Bank | over 2 years ago | deposit | +500 |
| Introductory resources for Singular Learning Theory | over 2 years ago | project donation | 50 |
| Holly Elmore organizing people for a frontier AI moratorium | over 2 years ago | project donation | 100 |
| Recreate the cavity-preventing GMO bacteria BCS3-L1 from precursor | over 2 years ago | project donation | 50 |
| WhiteBox Research: Training Exclusively for Mechanistic Interpretability | over 2 years ago | project donation | 150 |
| Activation vector steering with BCI | over 2 years ago | project donation | 150 |
| Manifund Bank | over 2 years ago | deposit | +500 |
| Avoiding Incentives for Performative Prediction in AI | over 2 years ago | project donation | 50 |
| Manifund Bank | over 2 years ago | deposit | +500 |
| WhiteBox Research: Training Exclusively for Mechanistic Interpretability | over 2 years ago | project donation | 70 |
| Alignment Is Hard | over 2 years ago | project donation | 70 |
| Introductory resources for Singular Learning Theory | over 2 years ago | project donation | 70 |
| Manifund Bank | over 2 years ago | deposit | +500 |
| WhiteBox Research: Training Exclusively for Mechanistic Interpretability | over 2 years ago | project donation | 100 |
| Compute and other expenses for LLM alignment research | over 2 years ago | project donation | 100 |
| Optimizing clinical Metagenomics and Far-UVC implementation. | over 2 years ago | project donation | 100 |
| Apollo Research: Scale up interpretability & behavioral model evals research | over 2 years ago | project donation | 160 |
| Apollo Research: Scale up interpretability & behavioral model evals research | over 2 years ago | project donation | 250 |
| Run five international hackathons on AI safety research | over 2 years ago | project donation | 250 |
| Holly Elmore organizing people for a frontier AI moratorium | over 2 years ago | project donation | 100 |
| Discovering latent goals (mechanistic interpretability PhD salary) | over 2 years ago | project donation | 400 |
| Discovering latent goals (mechanistic interpretability PhD salary) | over 2 years ago | project donation | 40 |
| Scoping Developmental Interpretability | over 2 years ago | project donation | 45 |
| Scoping Developmental Interpretability | over 2 years ago | project donation | 1000 |
| Scoping Developmental Interpretability | over 2 years ago | project donation | 455 |
| Joseph Bloom - Independent AI Safety Research | over 2 years ago | project donation | 250 |
| Joseph Bloom - Independent AI Safety Research | over 2 years ago | project donation | 100 |
| Joseph Bloom - Independent AI Safety Research | over 2 years ago | project donation | 50 |
| Manifund Bank | over 2 years ago | deposit | +1000 |
| Agency and (Dis)Empowerment | over 2 years ago | project donation | 250 |
| Manifund Bank | over 2 years ago | deposit | +2000 |
| <e083e3b0-a131-4eaa-8a83-6a146a196432> | over 2 years ago | profile donation | 100 |
| Medical Expenses for CHAI PhD Student | over 2 years ago | project donation | 43 |
| <03fac9ff-2eaf-46f3-b556-69bdee303a1f> | over 2 years ago | profile donation | 50 |
| Manifund Bank | over 2 years ago | deposit | +900 |
| Manifund Bank | over 2 years ago | deposit | +100 |