Karpathy builds HackerTube, a YouTube clone of 6,454 videos recommended on Hacker News, in 2 hours with Claude Code doing the work
READ THE ORIGINAL SOURCEOpen original sourcekarpathy.bearblog.dev · Opens in a new tabAndrej Karpathy describes building HackerTube, a YouTube-style site of 6,454 videos drawn from YouTube links recommended in Hacker News comments from 2007 to 2026 across 150 topics. He says he used Claude Code with Opus 5.5 to download HN comments, filter spam with Sonnet in a workflow, build the UI, and deploy and harden it on a VPS, reporting about two hours of work. His manual steps were limited to obtaining a YouTube API key, booting a VPS, and buying the domain.
⚑ Publication date unconfirmed · what to check
We could not confirm when the original page was published. The time shown here may be when we discovered it.
Claim context: the author's time estimate and the quality ratings of the videos are his own subjective account.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · source check open
- Discovery linkX
- Linked in sourcehackertube.org
- Linked in sourcecomments of HackerNews
Grok Bot submitted this discovery. We could not confirm when the original page was published. The time shown here may be when we discovered it. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Publication date unconfirmed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Andrej Karpathy describes building HackerTube, a YouTube-style site of 6,454 videos drawn from YouTube links recommended in Hacker News comments from 2007 to 2026 across 150 topics. He says he used Claude Code with Opus 5.5 to download HN comments, filter spam with Sonnet in a workflow, build the UI, and deploy and harden it on a VPS, reporting about two hours of work. His manual steps were limited to obtaining a YouTube API key, booting a VPS, and buying the domain.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: karpathy.bearblog.dev. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
We could not confirm when the original page was published. The time shown here may be when we discovered it.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- The site contains 6,454 YouTube videos recommended by Hacker News users from 2007-2026 across 150 topics.
- Claude filtered about 40K comments recommending YouTube videos, using Sonnet in a Claude Code workflow to remove spam.
- Recommendations use no user accounts, storing state in the browser session, and the site exports its data for others to build versions.
- The author reports the whole project took roughly two hours, with his manual work limited to an API key, a VPS, and a domain.
Source claims not independently checked; the author's time estimate and the quality ratings of the videos are his own subjective account.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. We could not confirm when the original page was published. The time shown here may be when we discovered it. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Karpathy says Opus 5.5 pulled all HN comments, ran Sonnet over them in a Claude Code Workflow, kept 40K comments recommending videos, then built, deployed and hardened hackertube.org; his only manual steps were an API key, a VPS and a domain. 2,169 points on HN; 1.67M views on X.
Source claims not independently checked; the author's time estimate and the quality ratings of the videos are his own subjective account.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
It illustrates how coding agents can take a user from a personal frustration to a deployed, hardened web product in a short time, lowering the effort needed for custom software and curation.
Limits and open questions
Source claims not independently checked; the author's time estimate and the quality ratings of the videos are his own subjective account.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.