|
354 | 354 |
|
355 | 355 | 00:08:39 They use some stronger models.
|
356 | 356 |
|
357 |
| -00:08:41 And then there's a website called Find, P-H-I-N-D, that allows you to do some searching, |
| 357 | +00:08:41 And then there's a website called PHIND, P-H-I-N-D, that allows you to do some searching, |
358 | 358 |
|
359 | 359 | 00:08:45 that they've built their own custom model.
|
360 | 360 |
|
|
436 | 436 |
|
437 | 437 | 00:10:44 So everyone's just hunting for more tokens and I think this is part of their strategy for that.
|
438 | 438 |
|
439 |
| -00:10:49 And then there's also a CLAWD by Anthropic. |
| 439 | +00:10:49 And then there's also a CLAUDE by Anthropic. |
440 | 440 |
|
441 | 441 | 00:10:52 And then after that, you get into the, kind of the open source APIs as well.
|
442 | 442 |
|
|
688 | 688 |
|
689 | 689 | 00:18:29 They're not gonna get close, they're not close to 100% accurate on these types of tasks.
|
690 | 690 |
|
691 |
| -00:18:34 The idea of agents as well is another thing that you might build with a LengChain. |
| 691 | +00:18:34 The idea of agents as well is another thing that you might build with a LangChain. |
692 | 692 |
|
693 | 693 | 00:18:38 And the idea there is basically the agent is getting a task, coming up with a plan for that task,
|
694 | 694 |
|
|
810 | 810 |
|
811 | 811 | 00:22:04 If you look for him, you'll see all his different fine, his different fine tunes and things like that.
|
812 | 812 |
|
813 |
| -00:22:09 And there's a group called Noose, I think is how you pronounce it, N-O-U-S. |
| 813 | +00:22:09 And there's a group called Nous, I think is how you pronounce it, N-O-U-S. |
814 | 814 |
|
815 | 815 | 00:22:13 And they've got some of the fine tunes that are basically the highest performing ones
|
816 | 816 |
|
|
924 | 924 |
|
925 | 925 | 00:25:29 - Nope, they're concentrating on the product, which makes sense.
|
926 | 926 |
|
927 |
| -00:25:31 - Yeah, so then the other one is LLMafile, LLMafile.ai that you mentioned, |
| 927 | +00:25:31 - Yeah, so then the other one is LLamafile, LLamafile.ai that you mentioned, |
928 | 928 |
|
929 | 929 | 00:25:35 and this packages it up.
|
930 | 930 |
|
|
1594 | 1594 |
|
1595 | 1595 | 00:44:04 You know, it is super easy to get started.
|
1596 | 1596 |
|
1597 |
| -00:44:05 They have like a tool to like help you generate your DALI picture and actually you don't even have to figure |
| 1597 | +00:44:05 They have like a tool to like help you generate your DALL picture and actually you don't even have to figure |
1598 | 1598 |
|
1599 | 1599 | 00:44:10 out how to do the custom instructions yourself.
|
1600 | 1600 |
|
|
2232 | 2232 |
|
2233 | 2233 | 01:02:08 I just wanted to give a shout out one more thing, 'cause your Visidata reminded me of something
|
2234 | 2234 |
|
2235 |
| -01:02:12 I just came across called Btop. |
| 2235 | +01:02:12 I just came across called Bpytop. |
2236 | 2236 |
|
2237 | 2237 | 01:02:14 - Yep, yep, yep.
|
2238 | 2238 |
|
|
2242 | 2242 |
|
2243 | 2243 | 01:02:20 But yeah, it's like a nice visualization.
|
2244 | 2244 |
|
2245 |
| -01:02:24 There's also a Bhytop. |
| 2245 | +01:02:24 There's also a Bpytop. |
2246 | 2246 |
|
2247 | 2247 | 01:02:26 It's pretty amazing what people can do in the terminal.
|
2248 | 2248 |
|
|
2359 | 2359 | 01:04:59 (upbeat music)
|
2360 | 2360 |
|
2361 | 2361 | 01:05:17 --
|
2362 |
| - |
0 commit comments