swyx
@swyx.io
i want everyone to aspire to integrity, intensity, and intentionality. see also @latent.space
pls come speak at AIE whenever u have an AI talk to do!! we are doing AIE Europe in London next April if that's interesting for you!
even critical/negative takes are fine tbh. itd be a dream for both me and ben to host you at our conference.
even critical/negative takes are fine tbh. itd be a dream for both me and ben to host you at our conference.
September 26, 2025 at 7:29 PM
pls come speak at AIE whenever u have an AI talk to do!! we are doing AIE Europe in London next April if that's interesting for you!
even critical/negative takes are fine tbh. itd be a dream for both me and ben to host you at our conference.
even critical/negative takes are fine tbh. itd be a dream for both me and ben to host you at our conference.
came here from HN. love your posts so much man.
i'm interested in building a "new HN" on atproto. went to the website. disappointed to find that there's no developer info about it lol.
i'm interested in building a "new HN" on atproto. went to the website. disappointed to find that there's no developer info about it lol.
September 26, 2025 at 7:06 PM
came here from HN. love your posts so much man.
i'm interested in building a "new HN" on atproto. went to the website. disappointed to find that there's no developer info about it lol.
i'm interested in building a "new HN" on atproto. went to the website. disappointed to find that there's no developer info about it lol.
Reposted by swyx
this is from @swyx.io in announcing that he’s joining Cognition/Windsurf
it’s really good. goes into detail on model labs vs agent labs, sync vs async agents, and a whole lot more
www.swyx.io/cognition
it’s really good. goes into detail on model labs vs agent labs, sync vs async agents, and a whole lot more
www.swyx.io/cognition
Cognition: The Devin is in the Details
My thesis for the future of software dev agents. This is a hastily written blogpost done on not a lot of sleep, so pardon poor pacing and structure and typos and mistakes but just getting it out there...
www.swyx.io
September 9, 2025 at 2:18 PM
this is from @swyx.io in announcing that he’s joining Cognition/Windsurf
it’s really good. goes into detail on model labs vs agent labs, sync vs async agents, and a whole lot more
www.swyx.io/cognition
it’s really good. goes into detail on model labs vs agent labs, sync vs async agents, and a whole lot more
www.swyx.io/cognition
Reposted by swyx
Interesting post about this from @swyx.io and crew: www.latent.space/p/why-mcp-won
It seems like the next step up from llmstxt.org
I think the usefulness really depends on if you want repeatable output from your LLM or if you use the LLM to build repeatable process (like terraform for config).
It seems like the next step up from llmstxt.org
I think the usefulness really depends on if you want repeatable output from your LLM or if you use the LLM to build repeatable process (like terraform for config).
Why MCP Won
Learnings from Anthropic's extraordinarily successful Launch and Workshop
www.latent.space
March 11, 2025 at 3:35 PM
Interesting post about this from @swyx.io and crew: www.latent.space/p/why-mcp-won
It seems like the next step up from llmstxt.org
I think the usefulness really depends on if you want repeatable output from your LLM or if you use the LLM to build repeatable process (like terraform for config).
It seems like the next step up from llmstxt.org
I think the usefulness really depends on if you want repeatable output from your LLM or if you use the LLM to build repeatable process (like terraform for config).
Reposted by swyx
github.com/r002/r002.gi...
PS. I'm also a huge fan of artifacts (Seth even blogged ab this today! (seths.blog/2025/01/the-...)
For me, I ❤ leaving a "learning exhaust" (h/t: @swyx.io) of screenshots whenever I build things. Later, you can then look back on them all to see how far you've traveled.
PS. I'm also a huge fan of artifacts (Seth even blogged ab this today! (seths.blog/2025/01/the-...)
For me, I ❤ leaving a "learning exhaust" (h/t: @swyx.io) of screenshots whenever I build things. Later, you can then look back on them all to see how far you've traveled.
January 7, 2025 at 4:10 AM
github.com/r002/r002.gi...
PS. I'm also a huge fan of artifacts (Seth even blogged ab this today! (seths.blog/2025/01/the-...)
For me, I ❤ leaving a "learning exhaust" (h/t: @swyx.io) of screenshots whenever I build things. Later, you can then look back on them all to see how far you've traveled.
PS. I'm also a huge fan of artifacts (Seth even blogged ab this today! (seths.blog/2025/01/the-...)
For me, I ❤ leaving a "learning exhaust" (h/t: @swyx.io) of screenshots whenever I build things. Later, you can then look back on them all to see how far you've traveled.
Reposted by swyx
@swyx.io pitched the "React distro" thesis a few years ago:
www.swyx.io/react-distros
I think it's a reasonable take / mindset.
The issue is that the React team has effectively stopped supporting the way half the ecosystem uses React, docs/guidance-wise.
www.swyx.io/react-distros
I think it's a reasonable take / mindset.
The issue is that the React team has effectively stopped supporting the way half the ecosystem uses React, docs/guidance-wise.
React Distros
Why we no longer have frontend framework wars, and musing on the state of React metaframeworks today and tomorrow
www.swyx.io
January 26, 2025 at 5:31 PM
@swyx.io pitched the "React distro" thesis a few years ago:
www.swyx.io/react-distros
I think it's a reasonable take / mindset.
The issue is that the React team has effectively stopped supporting the way half the ecosystem uses React, docs/guidance-wise.
www.swyx.io/react-distros
I think it's a reasonable take / mindset.
The issue is that the React team has effectively stopped supporting the way half the ecosystem uses React, docs/guidance-wise.