My Workflow for Understanding LLM Architectures

A Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026

A Round Up And Comparison of 10 Open-Weight LLM Releases in Spring 2026

How To Build Your Own LLM Runtime From Scratch

If you have ever wanted to actually build an LLM inference runtime yourself — pack your own weights, own every barrier, capture your own CUDA graphs — this is what that journey looks like on an H100. A step-by-step tour of a small runtime called annotated-llm-runtime, and the three bugs that produced most of the annotations.

Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention

From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context Costs

From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates

Understanding How DeepSeek's Flagship Open-Weight Models Evolved

Announcing the OpenAI Learning Accelerator

Complexity and Scale in AI-Assisted Workflow Management: A Federated Learning Case Study

The paper investigates the use of a large language model (LLM) agent to automate the creation and execution of a federated learning workflow for medical image analysis. By generating a reviewable specification of constraints and acceptance criteria, the LLM produces an executable workflow, while a validation loop repairs failures and ensures conformance to the specification. Experiments on the FABRIC testbed demonstrate that the approach can detect silent errors—such as a run that trained 1,700 jobs on random tensors—that traditional failure-driven debugging would miss.

OpenSkill: Open-World Self-Evolution for LLM Agents

arXiv:2606. 06741v1 Announce Type: new Abstract: Self-evolving agents requires adaptation after deployment, but existing approaches assume a usable learning loop, such as curated skills, successful trajectories, or verifier signals.

Introducing improvements to the fine-tuning API and expanding our custom models program

We’re adding new features to help developers have more control over fine-tuning and announcing new ways to build custom models with OpenAI.

Context operations to architecture modelling output from large language models and evaluation criteria for their use in systems engineering design

The paper presents a framework of formal operations for assembling context in large language model (LLM)-based engineering design, involving modular context units such as policy prompts, reference units with persistence, and user questions with prompt vectoring. It also introduces a formal method for evaluating modelling-as-code LLM outputs, assessing compliance to intent from LLM answers and the support LLMs provide for systems architecture modelling.

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

arXiv:2608. 15591v1 Announce Type: new Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve.

Introducing gpt-oss

We’re releasing gpt-oss-120b and gpt-oss-20b—two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. Available under the flexible Apache 2.

How to Make Your Own JEV Model from an Open LLM

The article explains how to transform a small open‑source Qwen LLM into a fast, single‑pass text classifier by replacing its language‑modeling head with a JEV model. It provides a step‑by‑step guide to swapping the head, enabling the LLM to perform classification tasks efficiently. The process leverages the flexibility of open‑source models to create a lightweight, high‑performance classifier.