Dan Turkel
@daturkel.bsky.social
Machine learning, recommenders and personalization, music, books.
danturkel.com / Brooklyn, NY
danturkel.com / Brooklyn, NY
Here's a stab at it: github.com/simonw/llm/p...
Templates support interpolation in fragments by daturkel · Pull Request #1305 · simonw/llm
With this change, you can have a template with
fragments:
- $input
or
fragments:
- github:$input
This works beautifully for a url summarization template, which can be as simple as this:
system: You...
github.com
November 19, 2025 at 1:56 AM
Here's a stab at it: github.com/simonw/llm/p...
Alright I've tried combining my github.com/daturkel/llm... with a template gist.github.com/daturkel/4fc... but I cannot for the life of me get claude to consistently stop saying "Based on the webpage content," or "I'll fetch that webpage and summarize it for you" :(
GitHub - daturkel/llm-tools-exa: A tool plugin for LLM to support web search via Exa
A tool plugin for LLM to support web search via Exa - daturkel/llm-tools-exa
github.com
November 19, 2025 at 1:12 AM
Alright I've tried combining my github.com/daturkel/llm... with a template gist.github.com/daturkel/4fc... but I cannot for the life of me get claude to consistently stop saying "Based on the webpage content," or "I'll fetch that webpage and summarize it for you" :(
ha it was the process of writing the bash script that made me want to see if I could simplify. the script workaround works fine for now but I might hack around to see if it's possible to make this work in a template
November 18, 2025 at 11:15 PM
ha it was the process of writing the bash script that made me want to see if I could simplify. the script workaround works fine for now but I might hack around to see if it's possible to make this work in a template
The market is saturated, but for products which differentiate themselves with features or performance, people seem to be willing to convert at the drop of a hat. Lots of cursor fans switched to claude code seemingly overnight. This feels like a marketing failure (then again, i haven't used q either)
June 30, 2025 at 9:17 PM
The market is saturated, but for products which differentiate themselves with features or performance, people seem to be willing to convert at the drop of a hat. Lots of cursor fans switched to claude code seemingly overnight. This feels like a marketing failure (then again, i haven't used q either)
I got web search with exa working pretty easily too: github.com/daturkel/llm...
github.com
May 25, 2025 at 9:23 PM
I got web search with exa working pretty easily too: github.com/daturkel/llm...
I may give it a shot if you're open to it!
May 17, 2025 at 8:39 PM
I may give it a shot if you're open to it!
even apple is selling genai as the way to half-ass a gift for your spouse. there are so many appealing non-dystopian use-cases...why pick this? youtu.be/A0BXZhdDqZM?...
Apple Intelligence | Create memory movies | iPhone 16
YouTube video by Apple
youtu.be
December 3, 2024 at 3:10 AM
even apple is selling genai as the way to half-ass a gift for your spouse. there are so many appealing non-dystopian use-cases...why pick this? youtu.be/A0BXZhdDqZM?...
Your marketing worked on me—I was going to grab maybe 6 or 7 and then I decided screw it I'll get the bundle.
November 29, 2024 at 11:02 PM
Your marketing worked on me—I was going to grab maybe 6 or 7 and then I decided screw it I'll get the bundle.
Someone can take my photo in public and sell it, and we generally are on board with this. But we probably wouldn't want a billion dollar corporation to monetize photos taken of all people in public at all times. Same principle, different vibes.
November 29, 2024 at 3:20 AM
Someone can take my photo in public and sell it, and we generally are on board with this. But we probably wouldn't want a billion dollar corporation to monetize photos taken of all people in public at all times. Same principle, different vibes.
Unless your site is very complicated I think you should have more or less the same experience. It's python, not a punch-card powered mainframe!
November 29, 2024 at 3:09 AM
Unless your site is very complicated I think you should have more or less the same experience. It's python, not a punch-card powered mainframe!
Benedict Evans has a good essay about how principles don't always hold up at massive scale, which has been useful for me in thinking through some of these issues. www.ben-evans.com/benedictevan...
November 29, 2024 at 3:08 AM
Benedict Evans has a good essay about how principles don't always hold up at massive scale, which has been useful for me in thinking through some of these issues. www.ben-evans.com/benedictevan...
It does have hot reloading, and it's fairly fast. docs.getpelican.com/en/latest/pu...
Publish your site
Site generation: Once Pelican is installed and you have some content (e.g., in Markdown or reST format), you can convert your content into HTML via the pelican command, specifying the path to your ...
docs.getpelican.com
November 29, 2024 at 2:47 AM
It does have hot reloading, and it's fairly fast. docs.getpelican.com/en/latest/pu...
You probably found that Pelican and Nikola are the two dominant python choices. They're not as popular as Hugo and some others, but I've been using Pelican for a few years now with no problem. I find it a bit more hackable when I'm fluent in the language, which I'm not for Go etc
November 28, 2024 at 11:59 PM
You probably found that Pelican and Nikola are the two dominant python choices. They're not as popular as Hugo and some others, but I've been using Pelican for a few years now with no problem. I find it a bit more hackable when I'm fluent in the language, which I'm not for Go etc
That makes sense, I actually recall someone even saying that the research seemed to be outpacing the accessible implementations for sparse neural embeddings. Maybe once it's in sentence transformers, splade will be everywhere 😅
November 28, 2024 at 12:08 PM
That makes sense, I actually recall someone even saying that the research seemed to be outpacing the accessible implementations for sparse neural embeddings. Maybe once it's in sentence transformers, splade will be everywhere 😅
This is not how the industry will win the hearts and minds of its critics...
November 28, 2024 at 4:17 AM
This is not how the industry will win the hearts and minds of its critics...
Bluesky might not have some of the specific subsets of trolls that are now rampant on Twitter, but I don't think they'll solve the fact that people can be much meaner behind a screen and keyboard than they would be "irl" 🤕
November 28, 2024 at 2:43 AM
Bluesky might not have some of the specific subsets of trolls that are now rampant on Twitter, but I don't think they'll solve the fact that people can be much meaner behind a screen and keyboard than they would be "irl" 🤕
If all of this means better standards going forward for opt-outs, that could be a win for everyone.
November 28, 2024 at 2:39 AM
If all of this means better standards going forward for opt-outs, that could be a win for everyone.
I think the fairly indiscriminate use of internet data to train commercial generative models has brought awareness to and shifted opinion against similar (if more innocuous) practices that have existed for a while, and the industry may have to reckon with the resulting bad vibes.
November 28, 2024 at 2:38 AM
I think the fairly indiscriminate use of internet data to train commercial generative models has brought awareness to and shifted opinion against similar (if more innocuous) practices that have existed for a while, and the industry may have to reckon with the resulting bad vibes.
Whether I agree with it or not (and I'm still thinking it through), I think the reactions are to the principle of the collection and publication of these datasets in general, not exclusively to the HF dataset. I doubt the posters you're referring to would be thrilled about this one.
November 28, 2024 at 2:35 AM
Whether I agree with it or not (and I'm still thinking it through), I think the reactions are to the principle of the collection and publication of these datasets in general, not exclusively to the HF dataset. I doubt the posters you're referring to would be thrilled about this one.