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.

#986 submission_evaluation succeeded

https://github.com/firish/claude_code_vs

complete 2026-06-16 15:32:20
#985 submission_evaluation succeeded

https://www.theregister.com/security/2026/06/15/feds-freaked-over-fable-5-after-simple-fix-this-code-prompt-not-jailbreak-says-researcher/5255827

complete 2026-06-16 15:32:10
#984 submission_evaluation succeeded

https://github.com/brandoncarl/llm-jailbreaking/blob/main/On%20the%20Impossibility%20of%20Perfect%20Universal%20Guardians%20Against%20LLM%20Jailbreaks.pdf

complete 2026-06-15 15:34:33
#983 submission_evaluation succeeded

https://barvhaim.github.io/visual-ai-metrics/

complete 2026-06-15 15:34:27
#982 submission_evaluation succeeded

https://conan.sh

complete 2026-06-15 15:34:17
#981 submission_evaluation succeeded

https://leaddev.com/ai/observability-tools-werent-built-for-ai-debugging

complete 2026-06-15 15:34:07
#980 submission_evaluation succeeded

https://github.com/lolu1032/pantheon-skills

complete 2026-06-15 15:34:03
#979 submission_evaluation succeeded

https://shukla.io/blog/2026-06/byoa.html

complete 2026-06-15 15:33:57
#978 submission_evaluation succeeded

https://tectonforgeai2.vercel.app

complete 2026-06-15 15:33:52
#977 submission_evaluation succeeded

https://github.com/vagkaratzas/skills/blob/main/token-saviour/SKILL.md

complete 2026-06-15 15:33:43
#976 submission_evaluation succeeded

https://github.com/treenix-io/treenix

complete 2026-06-15 15:33:33
#974 submission_evaluation succeeded

https://pyinfra.com

complete 2026-06-15 15:33:09

Processing logs

Newest worker events first.

info / queued Submission evaluation queued. https://github.com/SunnyLich/Wisp-AI-Assistant / 2026-07-13 15:32:25
info / evaluating Running the AI evaluation. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:25
info / crawl_saved Saved crawl snapshot with status 200. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:25
info / queued Submission evaluation queued. https://github.com/pedroaugusto04/Kote / 2026-07-13 15:32:25
info / queued Submission evaluation queued. https://xysq.ai / 2026-07-13 15:32:25
info / queued Submission evaluation queued. https://github.com/openai/codex/issues/32806 / 2026-07-13 15:32:25
info / queued Submission evaluation queued. https://github.com/innovatorved/sayitdev / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://sanbox.cloud / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://github.com/hkjarral/AVA-AI-Voice-Agent-for-Asterisk / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://github.com/sin-ack/agent-run / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://github.com/cyrusNuevoDia/capn-hook / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://github.com/clawkwork/clawk / 2026-07-13 15:32:24
info / crawling Crawling https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:24
info / checking_duplicate Checking for an existing accepted listing. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:24
info / starting Started processing job. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:24
info / queued Submission evaluation queued. https://geohot.github.io//blog/jekyll/update/2026/07/12/i-love-llms.html / 2026-07-13 15:32:24
info / complete Processing job completed. https://shbhmrzd.github.io/ai/ml-foundations/llm-training/2026/07/11/using-the-trained-model.html / 2026-07-12 15:35:26
info / complete Rejected submission decision saved. https://shbhmrzd.github.io/ai/ml-foundations/llm-training/2026/07/11/using-the-trained-model.html / 2026-07-12 15:35:26
info / rejecting Saving rejected submission decision. https://shbhmrzd.github.io/ai/ml-foundations/llm-training/2026/07/11/using-the-trained-model.html / 2026-07-12 15:35:26
info / evaluation_saved Saved rejected evaluation with score 45. https://shbhmrzd.github.io/ai/ml-foundations/llm-training/2026/07/11/using-the-trained-model.html / 2026-07-12 15:35:26