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.

#2598 submission_evaluation succeeded

https://github.com/oxiKKK/re-goldsrc-won-launcher-1792

complete 2026-08-24 15:33:21

#2597 submission_evaluation succeeded

https://www.jitbit.com/alexblog/coding-was-never-the-bottleneck/

complete 2026-08-24 15:33:10

#2596 submission_evaluation succeeded

https://thinkrail.ai

complete 2026-08-24 15:33:05

#2595 submission_evaluation succeeded

https://developers.openai.com/api/docs/pricing

complete 2026-08-24 15:33:00

#2594 submission_evaluation succeeded

https://github.com/kgoedecke/doop

complete 2026-08-24 15:32:56

#2593 submission_evaluation succeeded

https://bidsonar.com/mcp

complete 2026-08-24 15:32:45

#2592 submission_evaluation succeeded

https://github.com/PeepSick/usb

complete 2026-08-24 15:32:35

#2591 submission_evaluation succeeded

https://github.com/AlpinDale/gpt2.cmake

complete 2026-08-24 15:32:29

#2590 submission_evaluation succeeded

https://github.com/thiagotigaz/ocr-it

complete 2026-08-24 15:32:19

#2589 submission_evaluation succeeded

https://github.com/KellerJordan/modded-nanogpt

complete 2026-08-23 15:34:51

#2588 submission_evaluation succeeded

https://www.microphone.computer

complete 2026-08-23 15:34:41

#2587 submission_evaluation succeeded

https://www.pagerduty.com/eng/evidence-over-anecdotes-running-a-b-tests-on-ai-agent-tooling/

complete 2026-08-23 15:34:36

Processing logs

Newest worker events first.

info / evaluation_saved Saved rejected evaluation with score 55. https://sketchvlm.github.io / 2026-04-29 05:29:00

info / evaluating Running the AI evaluation. https://sketchvlm.github.io / 2026-04-29 05:28:57

info / crawl_saved Saved crawl snapshot with status 200. https://sketchvlm.github.io / 2026-04-29 05:28:57

info / crawling Crawling https://sketchvlm.github.io. https://sketchvlm.github.io / 2026-04-29 05:28:57

info / checking_duplicate Checking for an existing accepted listing. https://sketchvlm.github.io / 2026-04-29 05:28:57

info / starting Started processing job. https://sketchvlm.github.io / 2026-04-29 05:28:57

info / complete Processing job completed. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:55

info / complete Accepted and published vLLM-Compile. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:55

info / publishing Publishing accepted listing. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:55

info / evaluation_saved Saved accepted evaluation with score 76. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:55

info / evaluating Running the AI evaluation. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:52

info / crawl_saved Saved crawl snapshot with status 200. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:52

info / crawling Crawling https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:51

info / checking_duplicate Checking for an existing accepted listing. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:51

info / starting Started processing job. https://docs.google.com/presentation/d/17WYU9T9qouY20zJg-7n_kV8DrMRJ2LHeNh_WXD6bUmc/view?slide=id.g38a7e5eff34_0_2508 / 2026-04-29 05:28:51

info / complete Processing job completed. https://appliedcompute.com/research/inference-benchmark / 2026-04-29 05:28:50

info / complete Accepted and published Benchmarking Inference Engines on Agentic Workloads. https://appliedcompute.com/research/inference-benchmark / 2026-04-29 05:28:50

info / publishing Publishing accepted listing. https://appliedcompute.com/research/inference-benchmark / 2026-04-29 05:28:50

info / evaluation_saved Saved accepted evaluation with score 86. https://appliedcompute.com/research/inference-benchmark / 2026-04-29 05:28:50

info / evaluating Running the AI evaluation. https://appliedcompute.com/research/inference-benchmark / 2026-04-29 05:28:46