Likely AI-generated. Pangram flags 100% of this text as AI-written.

l

Technical AI safety

🥭

Mejdi Sadriu

Not fundedGrant

$0raised

José Wheeler

Decoding Logic: Mechanistic Interpretability in LLMs in a research program

Identifying and auditing reasoning circuits in LLMs within Algoverse 2026 using Sparse Autoencoders (SAEs).

Science & technology Technical AI safety

$0 raised

🐌

Sergey

Empirical econ - applied AI transition for quantitative econometrician

Fund demonstrated/rigorous quantitative researcher (already run reproduction/audit pipelines on published economics) for 6-month AI safety transition, shipping

Technical AI safety

$33K raised

Matthew Farr

MoSSAIC

Probing possible limitations and assumptions of interpretability | Articulating evasive risk phenomena arising from adaptive and self modifying AI

Science & technology Technical AI safety AI governance Global catastrophic risks

$0 raised

Aditya Raj

6-month research funding to challenge current AI safety methods

Current LLM safety methods—treat harmful knowledge as removable chunks. This is controlling a model and it does not work.

Technical AI safety Global catastrophic risks

$0 raised