The first step is SFTing our general-purpose 1.3B chat model on the right mixture. We iterated over many open-source datasets to find the ideal mix. This is great to raise performance, but also makes the model extremely verbose (>10k tokens on average).
CODE
-
GitHub Integration Coming Soon for AI Development
By
–
We'll have GitHub integration soon! And thanks for the nice feedback
-
Custom MCP Development Without Search or Fetch Tools
By
–
I want to add a custom MCP that doesn’t require /search or /fetch.
-
Jeff Dean praises Stanford’s CS336 Language Models from Scratch course
By
–
Very cool thread about the CS336 Language Models from Scratch course at Stanford taught by @percyliang et al. Makes me wish I was a student again!
-
Golang compatibility concerns with Textualizeio platform choice
By
–
If you use golang then you don't get to use @textualizeio
, so you might wanna rethink that… -
Google VideoPrism tool for automated video scene segmentation
By
–
Aprovechando la salida del nuevo modelo opensource de Google VideoPrism, para análisis de vídeo, me he programado una herramienta que a partir de analizar la similitud de los embeddings obtenidos corta el vídeo en sus diferentes escenas.
— Carlos Santana (@DotCSV) 24 juin 2025
Idealmente en un futuro usaré la… pic.twitter.com/LTbgrM2RXqAprovechando la salida del nuevo modelo opensource de Google VideoPrism, para análisis de vídeo, me he programado una herramienta que a partir de analizar la similitud de los embeddings obtenidos corta el vídeo en sus diferentes escenas. Idealmente en un futuro usaré la
-
Documentation Pages Designed Specifically for LLMs
By
–
We also write some docs pages specifically designed for LLMs — more concise and code-heavy than when we write for humans. E.g
-
Curating llms.txt Files for Optimal LLM Usefulness
By
–
The idea is that llms.txt is manually created/curated to have the exact info an LLM would find most useful. It's a bit of work to get right, but in my experience it's extremely helpful in practice (all our projects have carefully written llms.txt files).
-
Python Tool for Inlining Links in Documentation Files
By
–
If you want to full set of info, we recommend using the python tool we provide to create a version of the file with the links inlined, and tell your users how to use it. E.g we do this for fasthtml.