HN fodokidza 23d ago

Zero Weights Graph Language Engine (MSE-GLM)

MSE-GLM: interpretable graph-based language model alternative to standard neural networks. Provides explainability and deterministic output without floating-point weights.

LB role-confusion.github.io via LolPython 23d ago

Prompt Injection as Role Confusion

ICML 2026 research paper explaining prompt injection attacks as role confusion in LLMs, enabling new attack predictions and mechanistic interpretability insights.

HN Jeff9James 23d ago

Super AI Agentic Android App (BYOK)

Agentic Android app with memory, knowledge base, UI automation, MCP server support, local model compatibility. Bring-your-own-key architecture.

HN x312 23d ago

Prompt Injection as Role Confusion

ICML 2026 research paper on prompt injection attacks driven by role confusion in LLMs, with mechanistic interpretability implications.

HN raezil 23d ago

Go-Harness

Deterministic, local-first autonomous software engineering runtime combining orchestration with LLM reasoning via staged pipelines.

HN Pattaya 23d ago

The Coming Enshittification of AI

Opinion piece on commercial degradation of AI services, using Meta platform ads as analogy for declining user experience.