Josh
@joshsaintjacque.com
Seattle-area Staff Software Engineer working mostly on web applications. I work mostly in Ruby on Rails and React. Interested in AI and LLM discussions.
I sometimes write on joshsaintjacque.com.
I sometimes write on joshsaintjacque.com.
Man ChatGPT cuts deep 🥲
September 26, 2025 at 3:16 PM
Man ChatGPT cuts deep 🥲
It's neat that Tailwind has child selectors and all but I wonder if at this point you should just use a stylesheet.
September 20, 2025 at 3:01 AM
It's neat that Tailwind has child selectors and all but I wonder if at this point you should just use a stylesheet.
I love how extreme these opinions are. Like, sometimes an OS update is just an OS update.
September 16, 2025 at 7:29 PM
I love how extreme these opinions are. Like, sometimes an OS update is just an OS update.
Quote title screens important to you
April 7, 2025 at 7:46 AM
Quote title screens important to you
I liked the fish. And yes my back hurts. 😎
January 30, 2025 at 8:28 PM
I liked the fish. And yes my back hurts. 😎
Here, have whatever this is
January 29, 2025 at 5:14 AM
Here, have whatever this is
Wiring up an image gen AI model to a bluesky feed might be a good use case
January 29, 2025 at 4:50 AM
Wiring up an image gen AI model to a bluesky feed might be a good use case
It's the best I could come up with on short notice.
January 29, 2025 at 4:46 AM
It's the best I could come up with on short notice.
Here's the same prompt using `isDog`. Still looks like it got it, no? For reference, this is a clean thread via 4o.
January 13, 2025 at 11:18 PM
Here's the same prompt using `isDog`. Still looks like it got it, no? For reference, this is a clean thread via 4o.
That’s a good point. People aren’t used to consulting a computer the way they would a person (understanding it can be wrong) and verifying accordingly.
As an aside, in my test it took o1 (the reasoning model) to correctly answer this question.
As an aside, in my test it took o1 (the reasoning model) to correctly answer this question.
January 13, 2025 at 8:25 AM
That’s a good point. People aren’t used to consulting a computer the way they would a person (understanding it can be wrong) and verifying accordingly.
As an aside, in my test it took o1 (the reasoning model) to correctly answer this question.
As an aside, in my test it took o1 (the reasoning model) to correctly answer this question.
Tim Sweeney is on to something.
January 13, 2025 at 12:49 AM
Tim Sweeney is on to something.
Seems like it did ok, no?
January 11, 2025 at 6:16 AM
Seems like it did ok, no?
The situation at Meta is actually awful. They prohibit "allegations of stupidity, intellectual capacity, and mental illness"... unless it's targeted at someone because of their gender or sexual orientation.
Call my daughter stupid? Not ok. Call her stupid because she's a girl? Perfectly fine.
Call my daughter stupid? Not ok. Call her stupid because she's a girl? Perfectly fine.
January 9, 2025 at 5:03 AM
The situation at Meta is actually awful. They prohibit "allegations of stupidity, intellectual capacity, and mental illness"... unless it's targeted at someone because of their gender or sexual orientation.
Call my daughter stupid? Not ok. Call her stupid because she's a girl? Perfectly fine.
Call my daughter stupid? Not ok. Call her stupid because she's a girl? Perfectly fine.
This is the level of discourse on AI right now. Block function working overtime.
December 28, 2024 at 8:43 PM
This is the level of discourse on AI right now. Block function working overtime.
Spend so many hours in Red Alert.
December 28, 2024 at 10:11 AM
Spend so many hours in Red Alert.
Meanwhile current gen models produce routinely produce complex code. Anyone who has worked with Claude/GPT-4o/o1 experiences this first hand every day. The take that their useless because their training set isn't flawless is wild.
December 28, 2024 at 5:18 AM
Meanwhile current gen models produce routinely produce complex code. Anyone who has worked with Claude/GPT-4o/o1 experiences this first hand every day. The take that their useless because their training set isn't flawless is wild.
Not much sun in Seattle, not much vitamin D either. 🤷♂️
December 13, 2024 at 8:17 AM
Not much sun in Seattle, not much vitamin D either. 🤷♂️
I would want to learn more about the pluses/minuses of this approach. I'm sure there are some good reasons for it, but in my head I'm comparing to the simplest "Rails-y" approach I can think of.
December 4, 2024 at 4:54 AM
I would want to learn more about the pluses/minuses of this approach. I'm sure there are some good reasons for it, but in my head I'm comparing to the simplest "Rails-y" approach I can think of.