AI Wiki — Knowledge Base

I turned Qwen3.8-27B Q2_64 + llama.cpp into a fully TypeSafe AI-compatible Jev-like system. OpenAI API still intact! World’s first Vision-enabled Jev-like model! <10 GB VRAM, 170 ms on an RTX 3090 and ~140 tok/s in chat. 76% vs. 88% Jev-1.13 Acc. on a diverse 22,000-request typed-decision benchmark

Yesterday I released Bonsai-Llama-Jev - a Jev-like Typed Decision inference system for locally operated, sovereign AI. In my new typed-decision-bench, covering more than 22,000 decisions across 175 us

model-releasesr-localllama

23 Sept 2026

Search: “inference”

Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems

Meta-learning accelerates detector design optimization

How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure

Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise

Inferring Urban Mobility Interactions from Aggregated Dynamics

Inferred Generative-Process Diversity Predicts Correlated Failure Across Language Models

Learning to infer and manipulate through distributed whole-arm interaction in a soft robot

Infer Human's Intentions Before Following Natural Language Instructions

PETIMOT: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks

ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion

See, Infer, Intervene: Proactive World Modeling for Goal-Oriented Social Intelligence

Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills

Inferring Events from Time Series using Language Models

Inferring the Size of Large Language Models From Popular Text Memorization

Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies

Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditor

Inferring High-Level Events from Timestamped Data: Complexity and Medical Applications

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems

All Models

In View or Out of View? A Vision-Aware Filter that Infers and Reacts to the Human's Field of View

The agent-first cloud: why we built Managed Agents

GIFT: Glove-Inferred Force Transfer: Force-Aware Human-to-Robot Skill Transfer from a Wearable Sensing Glove to a Robot Hand Without Tactile Sensors

MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks

OpenAI Jalapeño: Better Than Nvidia Blackwell

CLAM: Causal Spatial Disaggregation to Infer Local Effects From Coarse Data

Scaling agentic AI: How UiPath built its high-performance GPU platform on AI Hypercomputer

Less Experts, Faster Decoding: Cost-Aware Speculative Decoding for Mixture-of-Experts

They Infer What You Meant: Models Represent Communicative Intent More Reliably Than They Act On It

Evaluating the Feasibility of Inferring Dietary Behavior Change Receptivity from Egocentric Images of Eating Environment

DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics

Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone

Posterior-First Neural PDE Simulation: Inferring Hidden Problem State from a Single Field

What’s new with the Cross-Cloud Network at Next ‘26

MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data

Inferring World Belief States in Dynamic Real-World Environments

Sense Less, Infer More: Agentic Multimodal Transformers for Edge Medical Intelligence

[Research] 2,788 tokens/s on a single RTX 5090 with a diffusion LLM — Introducing ORL (fully open source)

FlexiFlow: Bandit-based Model Switching in ML Workflows

Which alloy composition,what process parameters? Inferring the recipe from optimized metallic microstructure and texture

Inferring Soil Friction Angle from Robot Foot-Ground Force Histories: A Bayesian Inverse Approach to Proprioceptive Soil Sensing

Qwen3.8-27B: Using KV Cache Transplants to Boost Output Quality

AI-inferred expressed well-being and collective-action discourse in climate-change campaigns on X

From 'Who Is This User?' to 'What Does This Purchase Mean?': A Deployed Pipeline for Semantic User Profiling at Bank Scale

Inferring Affective Consciousness in an Artificial Agent: A Case Study

VISTA: Visually Inferred Spatial ConTact Attention for Contact-Rich Manipulation

Spike-based Belief Propagation in Nonlinear Dynamical Systems