Skip to content

Update 456-building-custom-gpts-with-python.txt #141

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 18, 2024
Merged

Update 456-building-custom-gpts-with-python.txt #141

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 8 additions & 9 deletions transcripts/456-building-custom-gpts-with-python.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -354,7 +354,7 @@

00:08:39 They use some stronger models.

00:08:41 And then there's a website called Find, P-H-I-N-D, that allows you to do some searching,
00:08:41 And then there's a website called PHIND, P-H-I-N-D, that allows you to do some searching,

00:08:45 that they've built their own custom model.

Expand Down Expand Up @@ -436,7 +436,7 @@

00:10:44 So everyone's just hunting for more tokens and I think this is part of their strategy for that.

00:10:49 And then there's also a CLAWD by Anthropic.
00:10:49 And then there's also a CLAUDE by Anthropic.

00:10:52 And then after that, you get into the, kind of the open source APIs as well.

Expand Down Expand Up @@ -688,7 +688,7 @@

00:18:29 They're not gonna get close, they're not close to 100% accurate on these types of tasks.

00:18:34 The idea of agents as well is another thing that you might build with a LengChain.
00:18:34 The idea of agents as well is another thing that you might build with a LangChain.

00:18:38 And the idea there is basically the agent is getting a task, coming up with a plan for that task,

Expand Down Expand Up @@ -810,7 +810,7 @@

00:22:04 If you look for him, you'll see all his different fine, his different fine tunes and things like that.

00:22:09 And there's a group called Noose, I think is how you pronounce it, N-O-U-S.
00:22:09 And there's a group called Nous, I think is how you pronounce it, N-O-U-S.

00:22:13 And they've got some of the fine tunes that are basically the highest performing ones

Expand Down Expand Up @@ -924,7 +924,7 @@

00:25:29 - Nope, they're concentrating on the product, which makes sense.

00:25:31 - Yeah, so then the other one is LLMafile, LLMafile.ai that you mentioned,
00:25:31 - Yeah, so then the other one is LLamafile, LLamafile.ai that you mentioned,

00:25:35 and this packages it up.

Expand Down Expand Up @@ -1594,7 +1594,7 @@

00:44:04 You know, it is super easy to get started.

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
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

00:44:10 out how to do the custom instructions yourself.

Expand Down Expand Up @@ -2232,7 +2232,7 @@

01:02:08 I just wanted to give a shout out one more thing, 'cause your Visidata reminded me of something

01:02:12 I just came across called Btop.
01:02:12 I just came across called Bpytop.

01:02:14 - Yep, yep, yep.

Expand All @@ -2242,7 +2242,7 @@

01:02:20 But yeah, it's like a nice visualization.

01:02:24 There's also a Bhytop.
01:02:24 There's also a Bpytop.

01:02:26 It's pretty amazing what people can do in the terminal.

Expand Down Expand Up @@ -2359,4 +2359,3 @@
01:04:59 (upbeat music)

01:05:17 --