--- schema: 1 type: video title: >- How I automate my own job at Hugging Face using agents — Niels Rogge, Hugging Face description: >- Thousands of GitHub issues, opened automatically, have produced exactly two negative replies. Niels Rogge works on what he calls the Google Drive to the hub team at Hugging Face, whose job is noticing that a paper's weights are sitting on Dropbox or Zenodo where nobody will find them, then asking the authors to publish on the hub instead. Hundreds of papers land on arXiv every day, so he automated himself. The useful part is that he built it twice, in opposite shapes, and explains why each time. The outreach half is a deterministic workflow: a model call at each step of the path he used to walk by hand, no agent framework at all, running nightly as a cron job on free GitHub Actions minutes, with tracing so he can inspect prompts, cost, and latency. He chose that because the prevailing advice when he built it was to avoid agents unless you genuinely need one. The follow up half, built recently, is the reverse. It is a fully autonomous loop whose main tool is bash, carrying one CLI, one skill, and a sandbox, fanned out so that every issue gets its own container. He is also candid that recipients are not told an agent wrote to them, on the grounds that it sends what he used to send himself and a disclosed bot tends to get closed unread. Speaker info: - https://x.com/NielsRogge - https://www.linkedin.com/in/niels-rogge-a3b7a3127/ - https://nielsrogge.github.io/ Timestamps: 0:00 - The Google Drive to the hub problem 1:59 - Paper pages, metadata, and discoverability 3:41 - Why manual outreach does not scale 4:29 - The workflow he was running by hand 5:19 - Workflow or agent, and why it is not binary 7:03 - Nightly cron jobs, and tracing cost and latency 8:46 - The flood of replies, and automating follow up 9:36 - Switching to a fully autonomous loop 10:25 - Bash, one CLI, one skill, one sandbox 12:06 - A container per issue, fanned out 13:49 - What researchers actually reply 15:32 - Migrated models, and a 400 gigabyte dataset 18:06 - Open models, agents over workflows, and evaluation --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/FLUoowDJg4I-how-i-automate-my-own-job-at-hugging-face-using-agents Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- canonical: >- https://liquidgold.cc/channel/aidotengineer/explore/video/how-i-automate-my-own-job-at-hugging-face-using-age-ba27904afc7f markdown: >- https://liquidgold.cc/channel/aidotengineer/video/how-i-automate-my-own-job-at-hugging-face-using-age-ba27904afc7f.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T04:56:17.392Z' language: null children: [] videoId: FLUoowDJg4I durationSeconds: 1237 publishedAt: '2026-08-20T15:30:35.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 28 endSeconds: 131 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=28' heldReason: rights - ordinal: 1 text: null startSeconds: 28 endSeconds: 131 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=28' heldReason: rights - ordinal: 2 text: null startSeconds: 142 endSeconds: 229 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=142' heldReason: rights - ordinal: 3 text: null startSeconds: 142 endSeconds: 229 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=142' heldReason: rights - ordinal: 4 text: null startSeconds: 319 endSeconds: 330 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=319' heldReason: rights - ordinal: 5 text: null startSeconds: 330 endSeconds: 431 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=330' heldReason: rights - ordinal: 6 text: null startSeconds: 431 endSeconds: 442 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=431' heldReason: rights - ordinal: 7 text: null startSeconds: 442 endSeconds: 527 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=442' heldReason: rights - ordinal: 8 text: null startSeconds: 442 endSeconds: 527 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=442' heldReason: rights - ordinal: 9 text: null startSeconds: 539 endSeconds: 582 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=539' heldReason: rights - ordinal: 10 text: null startSeconds: 594 endSeconds: 630 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=594' heldReason: rights - ordinal: 11 text: null startSeconds: 641 endSeconds: 729 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=641' heldReason: rights - ordinal: 12 text: null startSeconds: 641 endSeconds: 729 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=641' heldReason: rights - ordinal: 13 text: null startSeconds: 729 endSeconds: 741 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=729' heldReason: rights - ordinal: 14 text: null startSeconds: 741 endSeconds: 837 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=741' heldReason: rights - ordinal: 15 text: null startSeconds: 837 endSeconds: 849 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=837' heldReason: rights - ordinal: 16 text: null startSeconds: 949 endSeconds: 1088 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=949' heldReason: rights - ordinal: 17 text: null startSeconds: 949 endSeconds: 1088 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=949' heldReason: rights - ordinal: 18 text: null startSeconds: 1099 endSeconds: 1237 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=1099' heldReason: rights - ordinal: 19 text: null startSeconds: 1099 endSeconds: 1237 watch: 'https://liquidgold.cc/watch/FLUoowDJg4I?t=1099' heldReason: rights --- # How I automate my own job at Hugging Face using agents — Niels Rogge, Hugging Face Thousands of GitHub issues, opened automatically, have produced exactly two negative replies. Niels Rogge works on what he calls the Google Drive to the hub team at Hugging Face, whose job is noticing that a paper's weights are sitting on Dropbox or Zenodo where nobody will find them, then asking the authors to publish on the hub instead. Hundreds of papers land on arXiv every day, so he automated himself. The useful part is that he built it twice, in opposite shapes, and explains why each time. The outreach half is a deterministic workflow: a model call at each step of the path he used to walk by hand, no agent framework at all, running nightly as a cron job on free GitHub Actions minutes, with tracing so he can inspect prompts, cost, and latency. He chose that because the prevailing advice when he built it was to avoid agents unless you genuinely need one. The follow up half, built recently, is the reverse. It is a fully autonomous loop whose main tool is bash, carrying one CLI, one skill, and a sandbox, fanned out so that every issue gets its own container. He is also candid that recipients are not told an agent wrote to them, on the grounds that it sends what he used to send himself and a disclosed bot tends to get closed unread. Speaker info: - https://x.com/NielsRogge - https://www.linkedin.com/in/niels-rogge-a3b7a3127/ - https://nielsrogge.github.io/ Timestamps: 0:00 - The Google Drive to the hub problem 1:59 - Paper pages, metadata, and discoverability 3:41 - Why manual outreach does not scale 4:29 - The workflow he was running by hand 5:19 - Workflow or agent, and why it is not binary 7:03 - Nightly cron jobs, and tracing cost and latency 8:46 - The flood of replies, and automating follow up 9:36 - Switching to a fully autonomous loop 10:25 - Bash, one CLI, one skill, one sandbox 12:06 - A container per issue, fanned out 13:49 - What researchers actually reply 15:32 - Migrated models, and a 400 gigabyte dataset 18:06 - Open models, agents over workflows, and evaluation --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/FLUoowDJg4I-how-i-automate-my-own-job-at-hugging-face-using-agents Join our upcoming AI Engineer conferences (see https://ai.engineer landing page): - AIEi Shanghai, November 5–6 — the first for meeting top Chinese labs and engineers - AIE CODE in SF, November 10–12 — the top AI Coding conference returns - AIEi Sydney, December 7–8 — the first AIEi run alongside NeurIPS 2026 in Sydney --- Canonical: https://liquidgold.cc/channel/aidotengineer/explore/video/how-i-automate-my-own-job-at-hugging-face-using-age-ba27904afc7f · Channel: [AI Engineer](https://liquidgold.cc/channel/aidotengineer.md) > Search chunk text is held until public-source provenance is verified. ## Document chunks > Missing: no stored document chunks are available.