Ax Zachary Bamberger, Till R. Saenger, Gilad Morad, Ofra Amir, Brandon M. Stewart, Amir Feder 4/1/2026

STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts

STATe presents an interpretable inference-time-compute method using structured action templates to improve output diversity and reasoning control in tree-of-thoughts approaches for LLMs.

Ax Ruxiao Duan, Alex Wong 4/1/2026

Evidential Neural Radiance Fields

Neural radiance fields with evidential uncertainty quantification separating aleatoric and epistemic uncertainty.

Ax Dharshan Kumaran, Arthur Conmy, Federico Barbero, Simon Osindero, Viorica Patraucean, Petar Velickovic 4/1/2026

How do LLMs Compute Verbal Confidence

Study investigating how LLMs compute verbal confidence: timing of computation and relationship to answer quality.

HN 0x1997 4/1/2026

Burning Tokens Fast

User complaint about rapid token consumption in VS Code extension after update.

HN handfuloflight 4/1/2026

AI Agent Traps

Guide on building, training and deploying AI agents. Limited technical depth in provided excerpt.

HN jbarrow 4/1/2026

LFM2.5-350M: No Size Left Behind

LFM2.5-350M model released with 28T token pre-training, optimized for inference on CPUs and GPUs with tool use capabilities.

HN latentlie_747 4/1/2026

DefenseClaw: Secure Your OpenClaw

Enterprise governance layer for OpenClaw agents providing security controls for skills, MCP servers, and code execution.

HN shenli3514 4/1/2026

How Claude Code memory works

Explanation of how Claude Code memory system persists project context across sessions using disk-based file loading.

HN Ishymoto 4/1/2026

Codey-V2 is out – stable release

Codey-v2: Local AI coding agent for Android with daemon mode, RAG, git tools, voice, and self-refinement using three purpose-built models served via llama.cpp.