» Tag
llm
48 postsNo Standard Defines What to Record for an LLM Call, So I Built One
Johannes built a recording system for LLM calls to enhance AI traceability and reliability.
DeepSeek-V4-Flash 0731: Full Precision Lossless Performance Test
DeepSeek-V4-Flash-0731 can be run at full precision with 176 GB memory. The project focuses on efficiency and performance testing.
LLM-Generated Tests Influence Implementation Selection Outcomes
Key findings on the impact of LLM-generated tests on implementation selection and evaluation.
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.comHollow-LLM Attack: Ghost Weights That Fool Zero-Knowledge LLM Verification
The Hollow-LLM attack examines the impact of ghost weights on zero-knowledge verification.
Stigmergy: A Karpathy-Style LLM Wiki for Teams
Stigmergy introduces a team-focused LLM wiki inspired by Karpathy's concept, enhancing collaboration.
LLM in Product Search: Failures and Lessons Learned
Challenges and lessons learned from developing a natural language product search engine.
OpenCyvis: An Open-Source AI Phone Agent Running Your Own LLM
OpenCyvis turns Android into an AI phone, allowing natural language tasks while ensuring user data privacy and control.
Reverse Engineering the Closed GoodNotes Format Using LLMs
Export your data using an open-source Python toolkit that decodes GoodNotes format.
Coalent: An LLM Answer Cache That Invalidates When Source Changes
Coalent offers an LLM answer cache that automatically invalidates when sources change.
WMTrace: A New Tool for Understanding LLM Text Watermarks
WMTrace is a tool that analyzes LLM text watermarks, providing forensic detection and explainable analysis.