» Tag
llm
536 postsBuild a Bounded JSON Repair Loop for LLM Output in Python
Learn to build a bounded JSON repair loop for LLM outputs using Python.
Production RAG at Scale: Lessons from Processing 10,000+ Listings Daily
Insights on RAG pipeline stability, chunking strategies, and cost control from processing job listings.
DSLs Enhance Reliable Use of LLMs
DSLs play a crucial role in enhancing the reliability of LLMs in code generation.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comControl the Ideas, Not the Code
Antirez highlights the impact of AI on software development and the importance of focusing on ideas.
Routing LLM Traffic with TCP-Style Congestion Control
Explore an adaptive router that optimizes LLM traffic based on cost and speed.
An LLM Runtime Booting from USB: NightRun
NightRun is an LLM runtime that boots from USB, operating without an OS. It is written in Rust.
Measuring LLM Unlearning Depth with Activation Patching and UDS
The Unlearning Depth Score (UDS) quantifies LLM unlearning depth using activation patching.
Enhance Your LLM with DSLs
Boost your LLM's efficiency with DSLs. Explore effective data manipulation and continuous improvement strategies.
The Implications of Linguistic Illegibility for LLM Security
Linguistic illegibility in LLMs raises concerns about the reliability of security mechanisms. Taint tracking and other methods are proposed to enhance safety.
DeepSeek's new model sets a template for powerful LLMs that run lean
DeepSeek introduces Flash model 4.1, optimizing resource use while enhancing LLM capabilities.