program
api
program | api | |
---|---|---|
1 | 3 | |
297 | 151 | |
- | - | |
10.0 | 6.5 | |
12 months ago | 8 months ago | |
Java | MDX | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
program
-
First Contribution in an open-source project
Here's the repo: https://github.com/codinasion/program
api
-
Guidance: A guidance language for controlling large language models
Logit-bias guidance goes a long way -- LLM structure for regex, context-free grammars, categorization, and typed construction. I'm working on a hosted and model-agnostic version of this with thiggle
[0] https://thiggle.com
-
The Most Underrated Application of LLMs
We use a similar trick and expose it via an API. Much easier to parse when you can guarantee the shape of the output
[0] https://thiggle.com/
-
What we learned from using GPT for 500k+ classifications
I just released a zero-shot classification API built on LLMs https://github.com/thiggle/api. It always returns structured JSON and only the relevant categories/classes out of the ones you provide.
LLMs are excellent reasoning engines. But nudging them to the desired output is challenging. They might return categories outside the ones that you determined. They might return multiple categories when you only want one (or the opposite — a single category when you want multiple). Even if you steer the AI toward the correct answer, parsing the output can be difficult. Asking the LLM to output structure data works 80% of the time. But the 20% of the time that your code parses the response fails takes up 99% of your time and is unacceptable for most real-world use cases.
[0] https://twitter.com/mattrickard/status/1678603390337822722
What are some alternatives?
plc4x - PLC4X The Industrial IoT adapter
one-day-one-language - Cómo dar en un día tus primeros pasos en cada lenguaje de programación. Introducción, configuración e instalación, usos habituales, fundamentos, sintaxis y próximos pasos.
minestat - :chart_with_upwards_trend: A Minecraft server status checker
FlatBuffers - FlatBuffers: Memory Efficient Serialization Library
mal - mal - Make a Lisp
comby - A code rewrite tool for structural search and replace that supports ~every language.
GNOLL - GNOLL is an efficient dice notation parser for multiple programming languages that supports a wide set of dice notation
hof - Framework that joins data models, schemas, code generation, and a task engine. Language and technology agnostic.
svix-webhooks - The enterprise-ready webhooks service 🦀
nodebook - Nodebook - Multi-Lang Web REPL + CLI Code runner