J PRO

jrcrittenden

6 8

AI & ML interests

Memory, Systems Theory, Alignment

Recent Activity

updated a Space 11 days ago

jrcrittenden/repro-distributionally-robust-markov-games-avg-reward

published a Space 11 days ago

jrcrittenden/repro-distributionally-robust-markov-games-avg-reward

updated a bucket 11 days ago

jrcrittenden/repro-distributionally-robust-markov-games-avg-reward-artifacts

View all activity

Organizations

buckets 3

spaces 4

Repro - Distributionally Robust Markov Games with Average Reward

🎯

Collaborate with an AI agent to view and edit your project logbook

Drmg Repro

🎯

Show an interactive tracking dashboard

Repro - How much do language models memorize?

🎯

Browse and collaborate on language model memorization logs

Socrates' Crucible

🚀

Generate structured arguments from a prompt

models 0

None public yet

datasets 1

jrcrittenden/lm-memorization-repro

Viewer • Updated 11 days ago • 6 • 48

J PRO

AI & ML interests

Recent Activity

Organizations

buckets 3

jrcrittenden/drmg-repro-bucket

jrcrittenden/repro-distributionally-robust-markov-games-avg-reward-artifacts

jrcrittenden/repro-how-much-do-language-models-memorize-artifacts

Collections 5

Alignment Makes Language Models Normative, Not Descriptive

EmbeddingGemma: Powerful and Lightweight Text Representations

Alignment Makes Language Models Normative, Not Descriptive

EmbeddingGemma: Powerful and Lightweight Text Representations

spaces 4

Repro - Distributionally Robust Markov Games with Average Reward

Drmg Repro

Repro - How much do language models memorize?

Socrates' Crucible

models 0

datasets 1

jrcrittenden/lm-memorization-repro

J PRO

AI & ML interests

Recent Activity

Organizations

buckets 3 Sort: Recently updated

jrcrittenden/drmg-repro-bucket

jrcrittenden/repro-distributionally-robust-markov-games-avg-reward-artifacts

jrcrittenden/repro-how-much-do-language-models-memorize-artifacts

Collections 5

spaces 4 Sort: Recently updated

Repro - Distributionally Robust Markov Games with Average Reward

Drmg Repro

Repro - How much do language models memorize?

Socrates' Crucible

models 0

datasets 1

buckets 3

spaces 4