» Tag
language-models
22 postsMET: Advancing Multilingual Moral Reasoning with Culture-Aware Theory
MET introduces innovative frameworks for enhancing multilingual moral reasoning in language models.
Why Your Prompts Fail and How to Fix Them
Discover why your prompts fail and how to enhance their effectiveness.
Base Models Can Reason by Taking a Cue from Training Data
It has been demonstrated that base language models can enhance reasoning abilities using cues from training data.
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.comAccelerating LLM Inference with Lossless Speculative Decoding Methods
New lossless speculative decoding methods accelerate LLM inference without retraining.
I Gave an On-Device LLM a Search Tool, It Ignored It and Fabricated Data
A language model on iOS 27 ignored its search tool and fabricated data. Key lessons for developers emerge.
GLM-5.3 arrives with advanced cyber capabilities and finds vulnerability in Cursor
Z.ai's GLM-5.3 model has launched, finding a serious vulnerability in Cursor and showcasing advanced cybersecurity capabilities.
No cloud, no GPUs: Liquid AI's LFM2.5-2.6B model empowers edge devices
Liquid AI introduces LFM2.5-2.6B, a model that runs on local hardware without cloud or GPU dependencies.
Claude Opus 5's Odd Behavior: Writing with Ambiguous Input
The odd behavior of Claude Opus 5 when faced with ambiguous inputs was discovered. Important implications for engineers.
BABEL Codec: Fully Opens the Interior of the GPT-2 Model
The BABEL codec translates the internal state of the GPT-2 model into English, achieving 94.7% behavior reconstruction.
Prompt Injection: Threats and Solutions in Engineering
Prompt injection is a structural flaw threatening the security of language models. Solutions for developers are discussed.