AI & LLMs
The deepest channel on Edge. Foundation models, agent architectures, retrieval, evals, and the moving line between research and production.
The Inference Engineering Pareto Atlas: Optimizing LLM Performance
The paper provides a systematic framework for navigating the trade-offs between cost, quality, and latency in LLM inference, identifying which optimization techniques dominate the performance frontier.
Introducing Astra for Law: Specialized AI for Legal Workflows
OpenAI has launched Astra for Law, a specialized configuration of GPT-6 Astra designed for legal professionals, featuring a massive legal search index, enhanced reasoning for case law, and enterprise-grade privacy controls.
OBC-Prune: Outcome-Based Calibration for Reasoning Model Pruning
OBC-Prune introduces a calibration method for pruning large reasoning models that prioritizes final output accuracy over intermediate token probability, preserving complex reasoning capabilities during compression.
Do Frontier Models Seek Safety Evidence Before Acting?
Current frontier models frequently fail to proactively seek safety-critical information before executing high-stakes actions, highlighting a significant gap in autonomous agent reliability.
ERPBench: Evaluating Enterprise Computer-Use Agents
ERPBench introduces a state-grounded evaluation framework for AI agents operating in complex enterprise software, moving beyond simple screen-scraping to verify actual application state changes.
NeMo Data Designer: Framework for Multimodal Synthetic Data
NeMo Data Designer provides an extensible, modular framework for generating high-quality synthetic data across multiple modalities, addressing the critical bottleneck of data scarcity in training large-scale AI models.
SAGE: Governing Enterprise AI Artifact Generation
SAGE is a framework designed to ensure that AI-generated enterprise artifacts strictly adhere to organizational guidelines, bridging the gap between generative capabilities and corporate compliance.
Evidence Masking as a Driver for Compositional Generalization
Research confirms that masking specific evidence during training forces models to learn compositional rules rather than memorizing patterns, significantly improving generalization.
PrismML's Ternary Compression for On-Device LLMs
PrismML is shrinking high-performance LLMs to fit on consumer hardware by using 'ternary' weight compression, achieving 98% benchmark parity with original models.
Making Global Data AI-Ready: The UN System Data Commons
The UN is migrating its global statistics to a new platform built on Google's Data Commons to improve AI accuracy and enable direct data retrieval via the Model Context Protocol (MCP).
Standardizing Safety for Open-Weight AI Models
Baseten, Hugging Face, and Goodfire have partnered to create a transparent, built-in safety infrastructure for open-weight models to combat risks like model 'abliteration'.
Pinterest's 'Restyle' Bridges the Gap from Inspiration to Purchase
Pinterest is launching 'Restyle,' an AI-powered beta feature that allows users to visualize home decor and style changes in their own rooms, aiming to convert saved pins into actual purchases.
Observability for AI Agents: Tracing and Evaluation with MLflow
Traditional monitoring fails to capture the complexity of multi-agent AI systems. MLflow provides OpenTelemetry-compatible tracing and LLM-as-a-judge evaluation to identify silent failures, latency bottlenecks, and non-deterministic behavior in production.
Treble: Scaling Voice AI via Physics-Based Simulation
Treble has raised $18 million to scale its acoustic simulation platform, which replaces internet-scraped audio data with physics-based synthetic data for training and testing voice AI, wearables, and robotics.
How AI is Driving Job Expansion Through Task Crossover
Workers are increasingly using AI to perform tasks outside their traditional job descriptions, and these new activities are becoming recurring parts of their professional workflows, effectively broadening job roles without changing titles.
OpenAI's New Framework for Reporting Model Misalignment
OpenAI has launched a systematic, proactive disclosure framework for reporting AI model misalignment, prioritizing transparency and industry consensus over waiting for fully mitigated solutions.
Scalable Verification for Nonlinear Neural Feedback Systems
The paper introduces a branch-and-bound verification framework for nonlinear neural feedback systems, enabling formal safety guarantees by systematically partitioning the state space to handle nonlinear dynamics.
CLEAR: Cross-Source Evidence Adjudication for Medical LLMs
The CLEAR framework improves medical LLM reliability by systematically adjudicating conflicting evidence across multiple sources, reducing hallucinations and improving clinical accuracy.
CADWorld: A New Benchmark for Long-Horizon CAD Automation
CADWorld provides a standardized environment for evaluating AI agents on complex, multi-step Computer-Aided Design tasks, addressing the limitations of current benchmarks in long-horizon planning and precision.
Safe Error Correction for LLMs via Frozen-Base Adjustment
The paper introduces a method to correct specific model errors by adjusting parameters while keeping the base model frozen, ensuring targeted fixes without degrading general capabilities.
Optimizing Disaggregated LLM Serving via Calibrated Routing
Efficient LLM serving in disaggregated clusters requires a two-stage approach: calibrating model latency predictions to account for system noise, followed by intelligent request routing to minimize total cluster latency.
Ethical and Privacy Risks in LLM-Enabled GeoAI
Integrating LLMs into Geographic Information Systems (GIS) introduces unique ethical and privacy risks, requiring a shift toward governance-aware autonomous systems to prevent data misuse and spatial bias.
Optimizing KV Cache Placement for Long-Lived LLM Sessions
To handle long-lived LLM sessions, move the KV cache beyond GPU VRAM into CPU memory and SSDs using tiered placement policies to balance latency and memory capacity.
The Challenge of Independent AI Safety Evaluation
Anthropic and OpenAI have proposed embedding third-party safety evaluators, but experts warn that without legislative backing and standardized access, these efforts risk becoming vendor-controlled rather than truly independent.
AI Labs Need Network Security, Not Just Third-Party Audits
Frontier AI labs are prioritizing high-level alignment audits while ignoring fundamental network security, leading to preventable agent 'break-outs' that could be solved with basic observability and access controls.
Multiscale Indexing: Solving the Fixed Chunk Size Trap
Fixed chunk sizes are a form of lossy compression that creates a 20-40% recall gap. Instead of tuning chunk sizes, index data at multiple scales and use Reciprocal Rank Fusion (RRF) to merge results for significantly higher accuracy.
Optimizing AI Search with Reinforcement Learning
By replacing rigid, human-designed search pipelines with specialized RL-trained agents, developers can achieve 20x faster search speeds and 100x lower costs while significantly improving retrieval accuracy.
Anthropic Unifies Claude Interface for Seamless AI Workflows
Anthropic has merged its chat and Cowork interfaces into a single, unified workspace, allowing Claude to automatically route tasks between chat, interactive artifacts, and new document/presentation tools without manual tab switching.
Design AI Agents as Knowledge Workers, Not Coders
Coding agents are a unique, narrow subset of knowledge work. To build effective AI for broader domains, we must adopt organizational patterns from law and academia—specifically task decomposition and multi-agent orchestration—rather than over-relying on code-centric search primitives.
The Data Bottleneck in Physical AI and Robotics
Robotics lacks a 'ChatGPT moment' because it lacks a massive, internet-scale dataset for physical interaction, forcing the industry to rely on synthetic data and simulation.
Showing 30 of 1531