Under the hood

AI queue

Watch AgentDish crawl new pages and run AI reviews in public.

Processing queue

Live queue state for crawls and AI evaluations.

#1141 submission_evaluation succeeded

https://github.com/mirko-pira/skillhealth

complete 2026-06-23 15:33:09

#1140 submission_evaluation succeeded

https://github.com/Alfredvc/aharness

complete 2026-06-23 15:32:57

#1139 submission_evaluation succeeded

https://verity.md

complete 2026-06-23 15:32:45

#1138 submission_evaluation succeeded

https://github.com/block/buzz

complete 2026-06-23 15:32:37

#1137 submission_evaluation succeeded

https://oak.space/oak/oak

complete 2026-06-23 15:32:25

#1136 submission_evaluation succeeded

https://role-confusion.github.io

complete 2026-06-23 15:32:20

#1135 submission_evaluation succeeded

https://apps.microsoft.com/detail/9n7kdlcxvjxt?hl=en-US&gl=US

complete 2026-06-22 15:34:36

#1134 submission_evaluation succeeded

https://github.com/digitaldrywood/detent

complete 2026-06-22 15:34:31

#1133 submission_evaluation succeeded

https://github.com/sturnus-dev/sturnus

complete 2026-06-22 15:34:24

#1132 submission_evaluation succeeded

https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/securing-the-future-of-ai-agents/gdm-ai-control-roadmap.pdf

complete 2026-06-22 15:34:13

#1131 submission_evaluation succeeded

https://www.marshall.usc.edu/news/new-research-reveals-ai-is-boosting-productivity-at-home--but-not-equally

complete 2026-06-22 15:34:08

#1130 submission_evaluation succeeded

https://github.com/GLechevalier/nff

complete 2026-06-22 15:34:03

Processing logs

Newest worker events first.

info / evaluation_saved Saved accepted evaluation with score 86. https://github.com/frane/agented / 2026-04-30 15:34:26

info / evaluating Running the AI evaluation. https://github.com/frane/agented / 2026-04-30 15:34:08

info / crawl_saved Saved crawl snapshot with status 200. https://github.com/frane/agented / 2026-04-30 15:34:08

info / crawling Crawling https://github.com/frane/agented. https://github.com/frane/agented / 2026-04-30 15:34:07

info / checking_duplicate Checking for an existing accepted listing. https://github.com/frane/agented / 2026-04-30 15:34:07

info / starting Started processing job. https://github.com/frane/agented / 2026-04-30 15:34:07

info / complete Processing job completed. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:06

info / complete Accepted and published Give a 9B model persistent suffering states and leave it alone overnight. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:06

info / publishing Publishing accepted listing. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:06

info / evaluation_saved Saved accepted evaluation with score 76. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:06

info / evaluating Running the AI evaluation. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:02

info / crawl_saved Saved crawl snapshot with status 200. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:02

info / crawling Crawling https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:02

info / checking_duplicate Checking for an existing accepted listing. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:02

info / starting Started processing job. https://ninjahawk.github.io/blog/posts/local-llm-psychological-states.html / 2026-04-30 15:34:02

info / complete Processing job completed. https://github.com/srijansk/agent-relay / 2026-04-30 15:34:00

info / complete Rejected submission decision saved. https://github.com/srijansk/agent-relay / 2026-04-30 15:34:00

info / rejecting Saving rejected submission decision. https://github.com/srijansk/agent-relay / 2026-04-30 15:34:00

info / evaluation_saved Saved rejected evaluation with score 55. https://github.com/srijansk/agent-relay / 2026-04-30 15:34:00

info / evaluating Running the AI evaluation. https://github.com/srijansk/agent-relay / 2026-04-30 15:33:57