.txt Engineering blog.dottxt.ai

The control layer for AI

blog.dottxt.ai·5d

We read the JSON Schema spec so you don't have to

blog.dottxt.ai·1w·

Discuss: Lobsters, Hacker News

Do One Thing Well

blog.dottxt.ai·30w

Making LLMs Reliable: Building an LLM-powered Web App to Generate Gift Ideas

blog.dottxt.ai·59w

Say What You Mean: A Response to 'Let Me Speak Freely'

blog.dottxt.ai·63w

Extracting Financial Data from SEC 10-K Filings with LLMs

blog.dottxt.ai·65w

New rules for AI

blog.dottxt.ai·67w

Coding For Structured Generation with LLMs

blog.dottxt.ai·85w

Beating GPT-4 with Open Source

blog.dottxt.ai·86w

Prompt Efficiency - Using Structured Generation to get 8-shot performance from 1-shot.

blog.dottxt.ai·93w

How fast can grammar-structured generation be?

blog.dottxt.ai·95w

Structured Generation Improves LLM performance: GSM8K Benchmark

blog.dottxt.ai·99w

Coalescence: making LLM inference 5x faster

blog.dottxt.ai·105w