--- schema: 1 type: video title: 'x402 isn’t good (yet) — Jan Curn, Apify' description: >- Between the moment an x402 server verifies a payment signature and the moment it settles on the blockchain, nothing stops the buyer spending that money somewhere else. Jan Curn's point is that a client can mint a thousand signatures against one wallet, so any seller starting real work on the strength of a verification is exposed. The workaround is to do the work only after settlement, fine for a fixed price API call and awkward for anything slower. Curn is bullish enough on x402 to have shipped it two days before this talk, adding 20,000 Apify tools to a marketplace that previously carried about 2,000, and critical enough to spend the session on what it still gets wrong. He pitches it as a sequel to a talk here last year arguing that MCP was not good yet. The gaps compound. x402 wants HTTP 402 as the server's first response and MCP wants 401, and since one response cannot be both, companies stand up a second hostname purely for payments. Curn calls that an antipattern and asks how anyone would feel about a separate Amazon for every credit card. The original exact scheme charges a fixed fee per call, which does not fit tools that run for seconds or for hours, and the up to scheme meant to fix metered billing left the double spending window open anyway. Apify settled on charging in full and refunding the remainder, at the cost of a second chain transaction and a trust assumption pointing the wrong way. He is watching batch settlement, and has shipped a markdown page an agent reads to buy a prepaid token, deliberately not an API. Speaker info: - https://x.com/jancurn - https://www.linkedin.com/in/jancurn/ - https://apify.com/jancurn Timestamps: 0:00 - A callback to "MCP isn't good yet" 2:02 - Apify's 45,000 tools, and 10x'ing the x402 catalog 4:47 - The standards pileup, from L402 to Agent Pay 5:39 - Why crypto fits agentic payments, disputes included 8:25 - A 30 year old status code finally picked up 9:19 - The x402 flow, and the double spending window 11:10 - When x402 wants a 402 and MCP wants a 401 12:59 - Exact, then "up to", and what it still did not fix 13:55 - Charging in full, refunding the rest, and batch settlement 16:38 - AGI, an agent general interface 19:26 - Where the volume actually is today --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/h6mi88VrPtQ-youtube-37915f71960ed1a6b2ea 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/x402-isn-t-good-yet-jan-curn-apify-f3e46527d5f4 markdown: >- https://liquidgold.cc/channel/aidotengineer/video/x402-isn-t-good-yet-jan-curn-apify-f3e46527d5f4.md llms: null parent: 'https://liquidgold.cc/channel/aidotengineer.md' channel: aidotengineer updated: '2026-10-24T04:11:26.077Z' language: null children: [] videoId: h6mi88VrPtQ durationSeconds: 1248 publishedAt: '2026-09-01T19:00:09.000Z' searchChunks: - ordinal: 0 text: null startSeconds: 23 endSeconds: 125 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=23' heldReason: rights - ordinal: 1 text: null startSeconds: 23 endSeconds: 125 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=23' heldReason: rights - ordinal: 2 text: null startSeconds: 136 endSeconds: 292 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=136' heldReason: rights - ordinal: 3 text: null startSeconds: 136 endSeconds: 292 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=136' heldReason: rights - ordinal: 4 text: null startSeconds: 305 endSeconds: 349 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=305' heldReason: rights - ordinal: 5 text: null startSeconds: 360 endSeconds: 513 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=360' heldReason: rights - ordinal: 6 text: null startSeconds: 360 endSeconds: 513 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=360' heldReason: rights - ordinal: 7 text: null startSeconds: 360 endSeconds: 513 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=360' heldReason: rights - ordinal: 8 text: null startSeconds: 513 endSeconds: 523 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=513' heldReason: rights - ordinal: 9 text: null startSeconds: 523 endSeconds: 568 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=523' heldReason: rights - ordinal: 10 text: null startSeconds: 579 endSeconds: 675 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=579' heldReason: rights - ordinal: 11 text: null startSeconds: 675 endSeconds: 688 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=675' heldReason: rights - ordinal: 12 text: null startSeconds: 688 endSeconds: 785 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=688' heldReason: rights - ordinal: 13 text: null startSeconds: 795 endSeconds: 838 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=795' heldReason: rights - ordinal: 14 text: null startSeconds: 848 endSeconds: 1003 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=848' heldReason: rights - ordinal: 15 text: null startSeconds: 848 endSeconds: 1003 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=848' heldReason: rights - ordinal: 16 text: null startSeconds: 1003 endSeconds: 1013 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=1003' heldReason: rights - ordinal: 17 text: null startSeconds: 1013 endSeconds: 1168 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=1013' heldReason: rights - ordinal: 18 text: null startSeconds: 1013 endSeconds: 1168 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=1013' heldReason: rights - ordinal: 19 text: null startSeconds: 1178 endSeconds: 1248 watch: 'https://liquidgold.cc/watch/h6mi88VrPtQ?t=1178' heldReason: rights --- # x402 isn’t good (yet) — Jan Curn, Apify Between the moment an x402 server verifies a payment signature and the moment it settles on the blockchain, nothing stops the buyer spending that money somewhere else. Jan Curn's point is that a client can mint a thousand signatures against one wallet, so any seller starting real work on the strength of a verification is exposed. The workaround is to do the work only after settlement, fine for a fixed price API call and awkward for anything slower. Curn is bullish enough on x402 to have shipped it two days before this talk, adding 20,000 Apify tools to a marketplace that previously carried about 2,000, and critical enough to spend the session on what it still gets wrong. He pitches it as a sequel to a talk here last year arguing that MCP was not good yet. The gaps compound. x402 wants HTTP 402 as the server's first response and MCP wants 401, and since one response cannot be both, companies stand up a second hostname purely for payments. Curn calls that an antipattern and asks how anyone would feel about a separate Amazon for every credit card. The original exact scheme charges a fixed fee per call, which does not fit tools that run for seconds or for hours, and the up to scheme meant to fix metered billing left the double spending window open anyway. Apify settled on charging in full and refunding the remainder, at the cost of a second chain transaction and a trust assumption pointing the wrong way. He is watching batch settlement, and has shipped a markdown page an agent reads to buy a prepaid token, deliberately not an API. Speaker info: - https://x.com/jancurn - https://www.linkedin.com/in/jancurn/ - https://apify.com/jancurn Timestamps: 0:00 - A callback to "MCP isn't good yet" 2:02 - Apify's 45,000 tools, and 10x'ing the x402 catalog 4:47 - The standards pileup, from L402 to Agent Pay 5:39 - Why crypto fits agentic payments, disputes included 8:25 - A 30 year old status code finally picked up 9:19 - The x402 flow, and the double spending window 11:10 - When x402 wants a 402 and MCP wants a 401 12:59 - Exact, then "up to", and what it still did not fix 13:55 - Charging in full, refunding the rest, and batch settlement 16:38 - AGI, an agent general interface 19:26 - Where the volume actually is today --- Watch along with the corrected transcript, summary, timestamps and resources on this talk's official AIE page: https://ai.engineer/talks/h6mi88VrPtQ-youtube-37915f71960ed1a6b2ea 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/x402-isn-t-good-yet-jan-curn-apify-f3e46527d5f4 · 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.