AI Safety & Interpretability Lab

non-profit

https://aisilab.github.io/

aisilab

Activity Feed

AI & ML interests

Interpretability-informed control

Recent Activity

williambrach authored a paper about 14 hours ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

EvilScript new activity 3 days ago

aisilab/moltbook-files-new-language-signals:Add paper link, GitHub repository, and task category

EvilScript authored a paper 4 days ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

View all activity

Papers

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

View all Papers

williambrach

authored a paper about 14 hours ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

Paper • 2605.31170 • Published 7 days ago • 8

EvilScript

in aisilab/moltbook-files-new-language-signals 3 days ago

Add paper link, GitHub repository, and task category

#2 opened 3 days ago by

nielsr

EvilScript

authored a paper 4 days ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

Paper • 2605.31170 • Published 7 days ago • 8

EvilScript

submitted a paper to Daily Papers 4 days ago

Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion

Paper • 2605.31170 • Published 7 days ago • 8

EvilScript

updated a dataset 4 days ago

aisilab/moltbook-files-new-language-signals

Viewer • Updated 3 days ago • 518 • 230

lgalke

authored a paper 7 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

Paper • 2605.26045 • Published 11 days ago • 12

williambrach

authored a paper 7 days ago

The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment

Paper • 2605.07462 • Published 28 days ago • 3

EvilScript

authored a paper 9 days ago

The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment

Paper • 2605.07462 • Published 28 days ago • 3

EvilScript

submitted a paper to Daily Papers 9 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

Paper • 2605.26045 • Published 11 days ago • 12

EvilScript

authored a paper 9 days ago

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals

Paper • 2605.26045 • Published 11 days ago • 12

williambrach

updated a dataset 29 days ago

aisilab/moltbook-files

Viewer • Updated 29 days ago • 232k • 98

EvilScript

updated a dataset about 1 month ago

aisilab/moltbook-embeddings

Viewer • Updated about 1 month ago • 189k • 178

williambrach

published a dataset about 1 month ago

aisilab/moltbook-files

Viewer • Updated 29 days ago • 232k • 98

lgalke

updated a collection about 1 month ago

Moltbook Models

Collection

6 items • Updated May 4

AI & ML interests

Recent Activity

Papers

Team members 4

aisilab's activity

Add paper link, GitHub repository, and task category