app / likes
Spark
“Um, the only thing I like out of, out of Codex is the, is like Spark and like yeah.”
Public evidence record
Shawn Wang
Host · Latent Space
- Claims
- 500
- Episodes
- 64
- Shows
- 1
- Named items
- 20
Books, apps, and tools
The evidenced stack.
app / uses
Bank of America
“Yeah. I got, I got the tool. Uh, what, like, I hate, I use Bank of America. I hate bank, I hate the app. Mm-hmm. I hate the web. All banking websites just horrible.”
other / likes
Wiki approach
“I like the, the Wiki approach. Uh, my, I’m actually like, uh, you know, obviously I spent some my time at cognition, which, uh, you, you know very well.”
person / uses
Ted Chiang
“You were very excited because I read Ted Chiang over the holidays and I was very inspired by this short story called Understand, which apparently is, like, pretty old.”
app / uses
Overcast
“I used to use Overcast. So it would just link to the Overcast page.”
other / uses
Snip
“By the way, we use the snip count as a proxy for popularity, right? Because we have download counts, but for example, platforms like Spotify re-host our MP3 file.”
other / recommends
The Peel
“I think I strongly recommend Jack Bridger's Scaling DevTools, as well as Turner Novak's The Peel.”
other / recommends
Scaling DevTools
“I think I strongly recommend Jack Bridger's Scaling DevTools, as well as Turner Novak's The Peel.”
app / uses
AI News
“So that's what basically I use AI News for. I have a lot of prompts and a lot of steps and a lot of criteria and O1 just kind of checks through each kind of systematically.”
tool / built
Bolt.new
“It's funny because I built on top of the fork of Bolt.new that already has the multi LLM thing.”
other / uses
XML
“I use XML in other models as well, and it's just a really nice way to make sure that the thing that ends is tied to the thing that starts. That's the only way to do code fences where you're pretty sure example one start, example one end, that is one cohesive unit.”
app / uses
DevIn
“I used to tell people go to the DevIn demo and look at the four things that they offer and say each of those things is a startup.”
Claim ledger
What Shawn said.
33 transcript-backed records
01 / recommendation
Yeah, like I would actually advise and topic to tune down the marketing because also it’s, it is just a very good model and you don’t have to make so many marketing claims around it.
“Yeah, like I would actually advise and topic to tune down the marketing because also it’s, it is just a very good model and you don’t have to make so many marketing claims around it.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
02 / recommendation
Beyond that, I think honestly there is like, so I, I come from the sensibility of, I think everything that you are trying to do for agents experience now, which is the term that Matt Bowman and Nullify is trying to coin, is the same thing that you should have been doing for developer experience.
“Beyond that, I think honestly there is like, so I, I come from the sensibility of, I think everything that you are trying to do for agents experience now, which is the term that Matt Bowman and Nullify is trying to coin, is the same thing that you should have been doing for developer experience.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
03 / recommendation
Mentions personal use of Bank of America.
“Yeah. I got, I got the tool. Uh, what, like, I hate, I use Bank of America. I hate bank, I hate the app. Mm-hmm. I hate the web. All banking websites just horrible.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
04 / recommendation
Sometimes the, I don’t know if there’s a, this probably, you guys probably figured this out already, but since I, you need like a mute button.
“Sometimes the, I don’t know if there’s a, this probably, you guys probably figured this out already, but since I, you need like a mute button.”
- Speaker
- Shawn Wang
- Episode
- Cursor's Third Era: Cloud Agents
- Publisher
- Latent Space
05 / recommendation
You decide from me based on all the other people you know better than me. And I think every agent lab should basically end up doing this because that actually gives you extra power because you like people stop carrying or having loyalty with one lab.
“You decide from me based on all the other people you know better than me. And I think every agent lab should basically end up doing this because that actually gives you extra power because you like people stop carrying or having loyalty with one lab.”
- Speaker
- Shawn Wang
- Episode
- Cursor's Third Era: Cloud Agents
- Publisher
- Latent Space
06 / recommendation
Likes Wiki approach.
“I like the, the Wiki approach. Uh, my, I’m actually like, uh, you know, obviously I spent some my time at cognition, which, uh, you, you know very well.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
07 / recommendation
Mentions personal use of Ted Chiang.
“You were very excited because I read Ted Chiang over the holidays and I was very inspired by this short story called Understand, which apparently is, like, pretty old.”
- Speaker
- Shawn Wang
- Episode
- The First Mechanistic Interpretability Frontier Lab — Myra Deng & Mark Bissell of Goodfire AI
- Publisher
- Latent Space
08 / recommendation
So abusing the trust system is like setting up a trust system creates the damage from the trust system. And so I actually want to encourage people to try out MCP Inspector because all you got to do is actually just look at the traffic.
“So abusing the trust system is like setting up a trust system creates the damage from the trust system. And so I actually want to encourage people to try out MCP Inspector because all you got to do is actually just look at the traffic.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
09 / recommendation
Like they're, they're not normal servers in the, in the sense that they, they wrap some API and it's just easier to interact with those than to work at the APIs. And so I'll, I'll highlight the, the memory one first, just because like, I think there are, there are a few memory startups, but actually you don't need them if you just use this one.
“Like they're, they're not normal servers in the, in the sense that they, they wrap some API and it's just easier to interact with those than to work at the APIs. And so I'll, I'll highlight the, the memory one first, just because like, I think there are, there are a few memory startups, but actually you don't need them if you just use this one.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
10 / recommendation
Mentions personal use of Snip.
“By the way, we use the snip count as a proxy for popularity, right? Because we have download counts, but for example, platforms like Spotify re-host our MP3 file.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
11 / recommendation
Mentions personal use of Overcast.
“I used to use Overcast. So it would just link to the Overcast page.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
12 / recommendation
The only solution I know, which is to kind of keep a kind of warm pool of servers around, which is expensive, but maybe not so expensive because it's just CPUs.
“The only solution I know, which is to kind of keep a kind of warm pool of servers around, which is expensive, but maybe not so expensive because it's just CPUs.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
13 / recommendation
Recommends Scaling DevTools. Recommends The Peel.
“I think I strongly recommend Jack Bridger's Scaling DevTools, as well as Turner Novak's The Peel.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
14 / recommendation
Mentions personal use of AI News.
“So that's what basically I use AI News for. I have a lot of prompts and a lot of steps and a lot of criteria and O1 just kind of checks through each kind of systematically.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
15 / recommendation
Bash transcription, I would say Whisper, is something that you should be using on a as much as possible.
“Bash transcription, I would say Whisper, is something that you should be using on a as much as possible.”
- Speaker
- Shawn Wang
- Episode
- Latent.Space 2024 Year in Review
- Publisher
- Latent Space
16 / recommendation
Oh yeah, magically going to close the gap between the closed source and open source. So basically I think my advice to people is keep track of the slow cooking of benchmark language because the labs that are not that frontier will keep measuring themselves on last year's benchmarks and then the labs that are actually frontier will Tell you about [01:09:00] benchmarks you've never heard of and you'll be like, Oh, like, okay, there's, there's new, there's new territory to, to, to go on.
“Oh yeah, magically going to close the gap between the closed source and open source. So basically I think my advice to people is keep track of the slow cooking of benchmark language because the labs that are not that frontier will keep measuring themselves on last year's benchmarks and then the labs that are actually frontier will Tell you about [01:09:00] benchmarks you've never heard of and you'll be like, Oh, like, okay, there's, there's new, there's new territory to, to, to go on.”
- Speaker
- Shawn Wang
- Episode
- Latent.Space 2024 Year in Review
- Publisher
- Latent Space
17 / recommendation
he had like three dollar signs in the title I was like I can't do that so it's either building AI for the enterprise and then I also said the worst the most dangerous thing an AI startup can do is build for other AI startups which I think both of you will co-sign and I think basically the main thesis which I really liked was like go slow to go fast like here's the if you actually build for like security, compliance, personalization, usage analytics, latency budgets, and scale from the start then you're going to pay that cost now but eventually it's going to pay off in the long run and this is the actual insight you cannot do this later like if you build the easy thing first as an MVP it's like just ship it with whatever's easy to do and then you tack on the enterprise ready.
“he had like three dollar signs in the title I was like I can't do that so it's either building AI for the enterprise and then I also said the worst the most dangerous thing an AI startup can do is build for other AI startups which I think both of you will co-sign and I think basically the main thesis which I really liked was like go slow to go fast like here's the if you actually build for like security, compliance, personalization, usage analytics, latency budgets, and scale from the start then you're going to pay that cost now but eventually it's going to pay off in the long run and this is the actual insight you cannot do this later like if you build the easy thing first as an MVP it's like just ship it with whatever's easy to do and then you tack on the enterprise ready.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
18 / recommendation
talk about, but also kind of what we went through in our, in our call was I have PMF now, what is, is kind of what I've been saying. And so like, I think the first answer is hire a data scientist because we have to sort of figure out like from our data that you're now sitting on a ton of different customers and we don't really know the different customer segments.
“talk about, but also kind of what we went through in our, in our call was I have PMF now, what is, is kind of what I've been saying. And so like, I think the first answer is hire a data scientist because we have to sort of figure out like from our data that you're now sitting on a ton of different customers and we don't really know the different customer segments.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
19 / recommendation
Mentions personal use of XML.
“I use XML in other models as well, and it's just a really nice way to make sure that the thing that ends is tied to the thing that starts. That's the only way to do code fences where you're pretty sure example one start, example one end, that is one cohesive unit.”
- Speaker
- Shawn Wang
- Episode
- The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
- Publisher
- Latent Space
20 / recommendation
I think I want to restate the value proposition of Fireworks for people who are comparing you versus a raw GPU provider like a RunPod or Lambda or anything like those, which is like you create the developer experience layer and you also make it easily scalable or serverless or as an endpoint.
“I think I want to restate the value proposition of Fireworks for people who are comparing you versus a raw GPU provider like a RunPod or Lambda or anything like those, which is like you create the developer experience layer and you also make it easily scalable or serverless or as an endpoint.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
21 / recommendation
One thing that just occurred to me, so I'm a big fan of virtual mailboxes. I recommend that everybody have a virtual mailbox.
“One thing that just occurred to me, so I'm a big fan of virtual mailboxes. I recommend that everybody have a virtual mailbox.”
- Speaker
- Shawn Wang
- Episode
- Agents @ Work: Lindy.ai
- Publisher
- Latent Space
22 / recommendation
Blast from the past. It's always interesting how NeurIPS and all these academic conferences are sort of six months behind what people are actually doing, but conformal risk control, I would recommend people check it out.
“Blast from the past. It's always interesting how NeurIPS and all these academic conferences are sort of six months behind what people are actually doing, but conformal risk control, I would recommend people check it out.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
23 / recommendation
The way I put this is you should not be a prompt engineer because it is the goal of the big labs to put you out of a job.
“The way I put this is you should not be a prompt engineer because it is the goal of the big labs to put you out of a job.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
24 / recommendation
Prompt Layer, Braintrust, PromptFu, and HumanLoop, I guess would be my top picks from that category of people. And there's probably others that I don't know about.
“Prompt Layer, Braintrust, PromptFu, and HumanLoop, I guess would be my top picks from that category of people. And there's probably others that I don't know about.”
- Speaker
- Shawn Wang
- Episode
- The Ultimate Guide to Prompting
- Publisher
- Latent Space
25 / recommendation
I'll call out two recent papers which people might want to look into, which is a Salesforce yesterday released a paper called Diversity Empowered Intelligence, which is a, I think a shot at the bow for scale AI.
“I'll call out two recent papers which people might want to look into, which is a Salesforce yesterday released a paper called Diversity Empowered Intelligence, which is a, I think a shot at the bow for scale AI.”
- Speaker
- Shawn Wang
- Episode
- The Ultimate Guide to Prompting
- Publisher
- Latent Space
26 / recommendation
We just assume that people roughly know, but yeah, I think a dedicated episode directly on this, I think is something that's sorely needed. And then, you know, something I prompted Sander with is when I wrote about the rise of the AI engineer, it was actually a direct opposition to the rise of the prompt engineer, right?
“We just assume that people roughly know, but yeah, I think a dedicated episode directly on this, I think is something that's sorely needed. And then, you know, something I prompted Sander with is when I wrote about the rise of the AI engineer, it was actually a direct opposition to the rise of the prompt engineer, right?”
- Speaker
- Shawn Wang
- Episode
- The Ultimate Guide to Prompting
- Publisher
- Latent Space
27 / recommendation
Specifically because you brought up spreadsheets, I want to share my personal experience because I think Google has done a really good job that people don't know about, which is if you use Google Sheets, Gemini is integrated inside of Google Sheets and it helps you write formulas.
“Specifically because you brought up spreadsheets, I want to share my personal experience because I think Google has done a really good job that people don't know about, which is if you use Google Sheets, Gemini is integrated inside of Google Sheets and it helps you write formulas.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
28 / recommendation
Mentions personal use of DevIn.
“I used to tell people go to the DevIn demo and look at the four things that they offer and say each of those things is a startup.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
29 / recommendation
We should basically, when we're getting to the point where we're over-training models 100 times past Chinchilla ratio to optimize for inference, the next thing is actually like, hey, let's stop using so much memory when training because we're going to quantize it anyway for inference.
“We should basically, when we're getting to the point where we're over-training models 100 times past Chinchilla ratio to optimize for inference, the next thing is actually like, hey, let's stop using so much memory when training because we're going to quantize it anyway for inference.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
30 / recommendation
You just gave me an idea that Goodreads should be a data set because these are all novels that are commentaries about the contents of the novel.
“You just gave me an idea that Goodreads should be a data set because these are all novels that are commentaries about the contents of the novel.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
31 / recommendation
Yeah, I mean, like Kubernetes, like that point about Kubernetes, I will say as a former AWS employee, like it seems like it would be ideal for imbue to at some point make it more abstracted or agnostic because you're going to want to, you know, replicate your setup.
“Yeah, I mean, like Kubernetes, like that point about Kubernetes, I will say as a former AWS employee, like it seems like it would be ideal for imbue to at some point make it more abstracted or agnostic because you're going to want to, you know, replicate your setup.”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
32 / recommendation
You know, use Mistral to rephrase some existing part of your data sets, generate more tokens, anything like that, or any other form of synthetic data that you choose to mention? I think you also mentioned the large world model paper, right?
“You know, use Mistral to rephrase some existing part of your data sets, generate more tokens, anything like that, or any other form of synthetic data that you choose to mention? I think you also mentioned the large world model paper, right?”
- Speaker
- Shawn Wang
- Publisher
- Latent Space
33 / recommendation
Likes AI Breakdown.
“We love AI Breakdown as one of the best examples Daily podcasts to keep up on AI news, so we were especially excited to be back on Watch out and take”
- Speaker
- Shawn Wang
- Publisher
- Latent Space