The Highest Loop — swyx

AI Engineer · 7 min · 83 sentences · from YouTube's caption track

Each timecode opens YouTube at the start of that sentence. Line anchors (#s42) are the cue ids in the WebVTT, and every line carries its start and end seconds. All transcripts has every talk, and the whole corpus as one file.

  1. 00:07I need
  2. 00:13[music]
  3. 00:22I need I need baby I baby I
  4. 00:31[music]
  5. 00:31feel I feel
  6. 00:45[music]
  7. 00:58[music]
  8. 01:05In the beginning, there was the token.
  9. 01:10Then there was the chat.
  10. 01:13Then we learned to use tools.
  11. 01:17Then we learned to set goals.
  12. 01:18I'm skipping a few steps.
  13. 01:22And these days, we're all about automations.
  14. 01:24We're all about cron jobs and the loops and the rest of today on this live stream.
  15. 01:31Uh the uh those of you watching at home, uh we're going to be talking about software factories as well.
  16. 01:38So there's a lot of loop stacking.
  17. 01:41Uh I wrote this essay called Loopcraft.
  18. 01:43Uh I think Joel in the audience did a workshop on it yesterday.
  19. 01:47Can you still hear me?
  20. 01:47Are we good?
  21. 01:48Sorry, I I um had a mic slip.
  22. 01:51Um and I think this is something that is basically a core skill of AI engineer uh is defining what loops you're working in and figuring out whether that's the right level of extraction and when you're ready going up a loop in order to figure out the next level in productivity and scaling your inference
  23. 02:11and when you're finding issues going down a loop and going lower level in order to figure out reliability and fixing whatever bugs you you mind.
  24. 02:21If you want to simplify it, uh I have a I have a better analogy that will be less complicated.
  25. 02:27Uh it's literally just a stack of wild loops, right?
  26. 02:31I think all of you in in the audience and programmers will understand this.
  27. 02:35Uh and effectively, this is what we're here to do today.
  28. 02:38Um I expect our engineers, our leaders, our researchers, our founders um to all be understanding and recursing as a as a as a sort of human general intelligence all these loops that you guys are capable of of um going up and down.
  29. 02:55And that is why there's so much content.
  30. 02:59[laughter]
  31. 03:00Um I often tell people who who complain about uh the tracks, I'm not going to apologize for good content.
  32. 03:05uh it's up to you to decide and route yourself uh as to which level you currently working at and which level you're currently blocked on.
  33. 03:13Um so the thing that's occupying most of my time um recently and what I what I make the human analogy for is what is the human loop?
  34. 03:24Um and in the beginning there's the heartbeat when you when you're sort of in the womb you you sort of get that heartbeat that is the proof of life.
  35. 03:33Um then you learn to talk.
  36. 03:36Then we learn to use tools.
  37. 03:39Then we start to work.
  38. 03:40We eat, sleep, code, repeat or prompt.
  39. 03:44Um and then we start working in teams.
  40. 03:47We start working in small groups and families.
  41. 03:49We we've uh promoted the concept of tiny teams before and I think that is increasingly important with uh everybody.
  42. 03:56Um, and I think the interesting thing to think about is like the broader human projects as a whole.
  43. 04:03Like where are we all going?
  44. 04:04You know, extend out from your personal context, your family, your country, your company, whatever.
  45. 04:12Um, to the broader project of the human civilization and what we're building uh with collective intelligence.
  46. 04:17Uh, I think it's very interesting to uh consider that.
  47. 04:21So, um, I I think that's a little bit what I want to leave you with today.
  48. 04:25like the things that you're doing with coding are definitely crossing over to human life.
  49. 04:29Um the message of my last keynote at AI engineer was that the you know it's very much like agents that you see are working in one domain are definitely generalizing this year.
  50. 04:39Um this is the year that we are adding vertical tracks like you know AI in healthcare, AI in finance, AI in GTM uh we have a four deployed engineering track this uh today which I'm very excited about.
  51. 04:52Um all of this is meant to see how AI is just diffusing finally beyond coding.
  52. 04:58Okay.
  53. 04:59Um last world fair I gave you all an update on the stress curves uh of the of the organizers.
  54. 05:06Uh just to give you an idea this is um the first world uh first AI engineer in 2023.
  55. 05:11Uh this is sort of the the sales curves basically of like how people bought.
  56. 05:15Basically it was kind of linear.
  57. 05:17Then we had the first world fair 2024.
  58. 05:20uh about 2,000 people.
  59. 05:222025 uh was uh I think I maybe skipped uh skipped a few lines, but we're we're basically at 6,000.
  60. 05:30Um and if you sort of calculate uh sorry, we we we we aimed for 6,000.
  61. 05:34We actually crossed and going went to 7,000 today.
  62. 05:37Um and uh basically I asked you all to buy your tickets earlier.
  63. 05:40You did not.
  64. 05:42Um uh if you measure the Jenny coefficient, uh it has gone up and not down.
  65. 05:47That's the wrong direction.
  66. 05:48Um so if you
  67. 05:49[laughter]
  68. 05:49all if you all can just gather uh you know your yourselves and um you know join us earlier I think that would be great.
  69. 05:56Anyway um why we want to work at a conference why we why I work on a conference why you all come to a conference is basically the concept of the highest loop.
  70. 06:06Um I I will submit to you that the highest loop of all is to uh if I can make this slide work.
  71. 06:11Oh my god I'm gonna refresh.
  72. 06:15Okay.
  73. 06:16um uh that the highest loop is where humans come together to figure out what the next loop is, right?
  74. 06:22The loop that makes loops.
  75. 06:24Um so we organize a engineer summits all around the world.
  76. 06:27Uh this year we have summits in New York, summits in Paris, summits in Singapore.
  77. 06:32Um and you know again Melbourne and I'm forgetting one already Miami.
  78. 06:38Um and uh we organized this as a partners.
  79. 06:41We want you to organize it at in your home countries.
  80. 06:43We're we're hiring a partnerships team uh to do this and this is the highest loop of all which is the world's fair which is the summit of summits.
  81. 06:51So you're I'm very excited to welcome all of you today.
  82. 06:53Um I hope that you figure out your generative process for generating loops and propagate it down to your teams to your personal workflows to your lives.
  83. 07:02Thank you very much and enjoy the show.