Joshua Shew
@joshuashew.bsky.social
If your brain isn’t tired by the end of the day, you’re doing it wrong
he/him
2025 theme: Year of Foundations
he/him
2025 theme: Year of Foundations
I’m finally reading it!
November 9, 2025 at 9:27 PM
I’m finally reading it!
I should probably stop sinking time into this small Claude artifact I'm creating for my coworkers, but each hour I discover something new about creating Claude-powered artifacts and it gets better and better.
November 9, 2025 at 1:53 AM
I should probably stop sinking time into this small Claude artifact I'm creating for my coworkers, but each hour I discover something new about creating Claude-powered artifacts and it gets better and better.
I wish there was a way to manually trigger memory synthesis with the new project memory feature in Claude.ai.
I've been trying to use projects more, but I often have 20+ chats in an afternoon making progress on a new idea, and not having memory at that point feels limiting.
I've been trying to use projects more, but I often have 20+ chats in an afternoon making progress on a new idea, and not having memory at that point feels limiting.
November 9, 2025 at 12:49 AM
I wish there was a way to manually trigger memory synthesis with the new project memory feature in Claude.ai.
I've been trying to use projects more, but I often have 20+ chats in an afternoon making progress on a new idea, and not having memory at that point feels limiting.
I've been trying to use projects more, but I often have 20+ chats in an afternoon making progress on a new idea, and not having memory at that point feels limiting.
I really needed this new "extra usage" feature in Claude. Thank you @anthropic.com!
November 7, 2025 at 10:58 PM
I really needed this new "extra usage" feature in Claude. Thank you @anthropic.com!
I frequently wish for a distinction between like/dislike and agree/disagree on Bluesky. I end up liking a lot of stuff that I agree with but isn't really valuable reading. Conversely, there are some posts I read that I disagree with, but I am glad that I have read them.
November 7, 2025 at 10:45 PM
I frequently wish for a distinction between like/dislike and agree/disagree on Bluesky. I end up liking a lot of stuff that I agree with but isn't really valuable reading. Conversely, there are some posts I read that I disagree with, but I am glad that I have read them.
Kinda aggressively stated, but there’s an interesting feature request in here: filter posts by intractability
November 1, 2025 at 10:49 AM
Kinda aggressively stated, but there’s an interesting feature request in here: filter posts by intractability
I only had the vaguest notion of what double descent was before this video, and I feel like this brought me to the point where I'm overconfident in my understanding of the topic.
Still, better than nothing! And it's a really pretty video too.
Still, better than nothing! And it's a really pretty video too.
What the Books Get Wrong about AI [Double Descent]
YouTube video by Welch Labs
youtu.be
October 31, 2025 at 4:04 AM
I only had the vaguest notion of what double descent was before this video, and I feel like this brought me to the point where I'm overconfident in my understanding of the topic.
Still, better than nothing! And it's a really pretty video too.
Still, better than nothing! And it's a really pretty video too.
Bookmarking this so that I can share it next time aliens news comes around that warrants it.
Hank Green consistently delivers on science communication.
Hank Green consistently delivers on science communication.
Why it's Never Aliens
YouTube video by Hank Green
youtu.be
October 31, 2025 at 4:03 AM
Bookmarking this so that I can share it next time aliens news comes around that warrants it.
Hank Green consistently delivers on science communication.
Hank Green consistently delivers on science communication.
What a solid video essay. Well worth the watch (maybe on 1.5x speed) if you enjoyed Rogue One or Andor.
The Myth That Rogue One Shattered
YouTube video by ArTorr
youtu.be
October 31, 2025 at 4:01 AM
What a solid video essay. Well worth the watch (maybe on 1.5x speed) if you enjoyed Rogue One or Andor.
1. This is so cool
2. This is the first time a comment of mine has made it into a video. Not sure if that's a good thing or a bad thing tbh
2. This is the first time a comment of mine has made it into a video. Not sure if that's a good thing or a bad thing tbh
Why Do Redstoners Shove Mobs Inside Doors?
YouTube video by Purplers
youtu.be
October 31, 2025 at 3:57 AM
1. This is so cool
2. This is the first time a comment of mine has made it into a video. Not sure if that's a good thing or a bad thing tbh
2. This is the first time a comment of mine has made it into a video. Not sure if that's a good thing or a bad thing tbh
Just pushed an update to prod during peak usage hours for software that hasn't been touched for nearly a year at work 😬️
It went smoothly (and wasn't really high impact) but I seriously need to set up a dev environment for quick fixes and interating on things.
It went smoothly (and wasn't really high impact) but I seriously need to set up a dev environment for quick fixes and interating on things.
October 31, 2025 at 12:31 AM
Just pushed an update to prod during peak usage hours for software that hasn't been touched for nearly a year at work 😬️
It went smoothly (and wasn't really high impact) but I seriously need to set up a dev environment for quick fixes and interating on things.
It went smoothly (and wasn't really high impact) but I seriously need to set up a dev environment for quick fixes and interating on things.
The moral clarity you gain by seeing all of humanity as being clones of yourself, and you are all helping each other out.
October 29, 2025 at 1:47 AM
The moral clarity you gain by seeing all of humanity as being clones of yourself, and you are all helping each other out.
Finished the video splitting shortcut
October 26, 2025 at 12:23 PM
Finished the video splitting shortcut
Just discovered a-Shell today and it is amazing. I'm putting together a quick utility to make it easier to share videos with my friends in our group chats, and being able to put all the complexity in something not Shortcuts feels so good.
October 25, 2025 at 5:14 AM
Just discovered a-Shell today and it is amazing. I'm putting together a quick utility to make it easier to share videos with my friends in our group chats, and being able to put all the complexity in something not Shortcuts feels so good.
@anisota.net's stamina system is a fresh perspective on how to interface with social media, but maybe I'm using it wrong? I think I spend too much time on each post because I've only ever depleted the stamina once.
Maybe if I'm a member I can make the stamina last less for me.
Maybe if I'm a member I can make the stamina last less for me.
October 25, 2025 at 4:45 AM
@anisota.net's stamina system is a fresh perspective on how to interface with social media, but maybe I'm using it wrong? I think I spend too much time on each post because I've only ever depleted the stamina once.
Maybe if I'm a member I can make the stamina last less for me.
Maybe if I'm a member I can make the stamina last less for me.
Using @anisota.net slows me down so I read each post, and it exposes all the unrelated posts my feeds surface to me.
I need to be more disciplined in my "likes" because even the "For You" feed is serving me too much politics.
I need to be more disciplined in my "likes" because even the "For You" feed is serving me too much politics.
October 25, 2025 at 4:39 AM
Using @anisota.net slows me down so I read each post, and it exposes all the unrelated posts my feeds surface to me.
I need to be more disciplined in my "likes" because even the "For You" feed is serving me too much politics.
I need to be more disciplined in my "likes" because even the "For You" feed is serving me too much politics.
It happened again :/
Claude safety filter is sensitive when it comes to discussions about AI, I guess?
claude.ai/share/1b4d6f...
Claude safety filter is sensitive when it comes to discussions about AI, I guess?
claude.ai/share/1b4d6f...
October 25, 2025 at 4:20 AM
It happened again :/
Claude safety filter is sensitive when it comes to discussions about AI, I guess?
claude.ai/share/1b4d6f...
Claude safety filter is sensitive when it comes to discussions about AI, I guess?
claude.ai/share/1b4d6f...
I should come back to this later when I have the time.
Agents are Systems Software
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
Agents are Systems Software
timkellogg.me
October 25, 2025 at 3:55 AM
I should come back to this later when I have the time.
Reposted by Joshua Shew
Agents are Systems Software
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
Agents are Systems Software
timkellogg.me
October 25, 2025 at 1:42 AM
Agents are Systems Software
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
You're not supposed to build the yourself. They're too hard to build well. Just use a general agent, like Claude Code & Codex and customize it
Not everyone needs one.
timkellogg.me/blog/2025/10...
That moment when you figure out how to do something in a clever way and you have to check if your AI assistant of choice can figure it out too, given the information available to you at the time.
Micro benchmarking
Micro benchmarking
October 24, 2025 at 6:56 PM
That moment when you figure out how to do something in a clever way and you have to check if your AI assistant of choice can figure it out too, given the information available to you at the time.
Micro benchmarking
Micro benchmarking
Looks great. It’s a little finicky trying to post stuff from this interface, but I’ll try using is as my space to read posts for now.
October 24, 2025 at 6:49 PM
Looks great. It’s a little finicky trying to post stuff from this interface, but I’ll try using is as my space to read posts for now.
Recently I've been running into issues where Claude's output includes lists that should have newlines in them but don't. I haven't tried this in the API enough to see if this is a rendering issue or an issue with the output itself...
October 24, 2025 at 6:35 PM
Recently I've been running into issues where Claude's output includes lists that should have newlines in them but don't. I haven't tried this in the API enough to see if this is a rendering issue or an issue with the output itself...
I'm trying out anisota.net for the first time. Great experience!
- stamina-based social media engagement is the right model for me
- there was plenty to try and experience without paying
- lots of customizability in settings, but you don't have to dig to learn. "l" to like a post was intuitive.
- stamina-based social media engagement is the right model for me
- there was plenty to try and experience without paying
- lots of customizability in settings, but you don't have to dig to learn. "l" to like a post was intuitive.
anisota for Bluesky & ATProto
a new, experimental way to use social media
anisota.net
October 24, 2025 at 6:30 PM
I'm trying out anisota.net for the first time. Great experience!
- stamina-based social media engagement is the right model for me
- there was plenty to try and experience without paying
- lots of customizability in settings, but you don't have to dig to learn. "l" to like a post was intuitive.
- stamina-based social media engagement is the right model for me
- there was plenty to try and experience without paying
- lots of customizability in settings, but you don't have to dig to learn. "l" to like a post was intuitive.
This was fun!
In my view, 80+ is indicative of a lack of curiosity with one of the most interesting and accessible technologies of our time.
www.aipuritytest.org
In my view, 80+ is indicative of a lack of curiosity with one of the most interesting and accessible technologies of our time.
www.aipuritytest.org
October 24, 2025 at 4:24 PM
This was fun!
In my view, 80+ is indicative of a lack of curiosity with one of the most interesting and accessible technologies of our time.
www.aipuritytest.org
In my view, 80+ is indicative of a lack of curiosity with one of the most interesting and accessible technologies of our time.
www.aipuritytest.org
I was pleasantly surprised to hear Ezra Klein take AI x-risk as seriously as he did in this interview. EY isn't a great commumicator for the broader public, but Klein did his best to direct the conversation in a positive direction.
How Afraid of the A.I. Apocalypse Should We Be?
Podcast Episode · The Ezra Klein Show · 10/15/2025 · 1h 8m
podcasts.apple.com
October 24, 2025 at 3:30 AM
I was pleasantly surprised to hear Ezra Klein take AI x-risk as seriously as he did in this interview. EY isn't a great commumicator for the broader public, but Klein did his best to direct the conversation in a positive direction.