Engineering
Building Self-Improving Tax Agents With Codex
OpenAI and Thrive Holdings detailed a collaboration to build Tax AI, a self-improving agent built on Codex that automates preparation…
Engineering
How Anthropic Runs Large-Scale Code Migrations With Claude Code
Anthropic described how its engineers use Claude Code to execute large-scale codebase migrations, citing examples such as Labs co-lead Mike…
Engineering
AI Model Releases — Week of July 9, 2026
A Hugging Face blog roundup published July 9, 2026 surveyed a week of frontier model releases, highlighting a shift toward…
Engineering
Meta’s AI Storage Blueprint at Scale
Meta redesigned its blob-storage architecture to address performance bottlenecks in AI workloads by implementing a unified metadata schema backed by…
Engineering
llm-coding-agent: Building a Coding Agent on the LLM Framework
Simon Willison released llm-coding-agent, a coding agent library built on top of his LLM Python framework. The agent itself was…
Engineering
Cohere Transcribe Arabic: A New Open-Source Arabic Speech Recognition Model
Cohere Labs released Cohere Transcribe Arabic, an open-source automatic speech recognition model built on a 2-billion-parameter encoder-decoder architecture. Training data…
Engineering
Triton Plugin Extensions: Enabling TLX and Custom Compiler Passes Out of the Box
PyTorch-Triton 3.7 introduces a plugin extensions system that lets developers dynamically load custom compiler passes, dialects, and operations into upstream…
Engineering
Separating signal from noise in coding evaluations
OpenAI audited the widely used SWE-Bench Pro coding benchmark and found that roughly 30% of its 731 public tasks are…
Engineering
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
NVIDIA released Nemotron 3 Embed, a family of open embedding models built for enterprise retrieval and agentic AI systems, with…
Engineering
What building Shippy taught us about building agents
The Ai2 team detailed the architecture behind Shippy, a maritime AI agent, which they split into a system-prompt-defined soul, markdown-file…
Engineering
Model Routing Is Simple. Until It Isn’t.
IBM Research argues that routing requests among multiple LLMs in agentic systems is more complex than simple task classification, since…
Engineering
J-Space: Yet Another LLM Mind Reader?
J-Space introduces the Jacobian lens (J-lens), a mechanistic interpretability technique that identifies verbalizable concepts within language model activations. The method…