LLM post-training - Page 14
Stories from LLM post-training come first, newest first, then stories from connected topics (Kimi K3, Qwen3.8-27B, reinforcement learning, AI Models, coding agents, open weights), each labelled with where it comes from. This view is not indexed by search engines.
Latest
Z.ai Launches GLM-Legal, an Agentic Legal Model Built on GLM-5.3-Flash
Z.ai unveils GLM-Legal, an agentic legal model built on GLM-5.3-Flash. It claims a 19.2% all-pass rate on Harvey LAB, up 12.5 points on its base model.
Meta Launches Muse Wonder and Muse Wonder Full, Its “Most Capable Models to Date”, Built for AI Agents
Meta launches Muse Wonder and Muse Wonder Full, "our most capable models to date", for agentic tasks, via the Meta Model API and Muse Code from today.
Sakana AI’s MASS Lets a 27B Model Train Itself Using a Team of Its Own Subagents; the Results Are Self-Reported
Sakana AI's MASS lets one 27B model run, judge and learn from a team of its own subagents. Gains are Sakana's own, in a preprint not yet peer-reviewed.
Reverse Engineer Anything: The Open-Source MCP Tool for AI Agents
REA is an open-source MCP tool that lets AI agents inspect software. What the project says it does, how to set it up, its limits and legal risks.
Sperid Labs Releases Iris-3B, an Open Image Model That Skips the VAE
Sperid Labs released Iris-3B, a 3B image model with no VAE. Its paper finds no clear gain for depth or restoration. Code and weights are open.
LAION Releases Open Voice Converter Built on Resemble AI’s Chatterbox
LAION released an open voice-conversion model built on Chatterbox. The scores are LAION's own, and match to the target voice fell from 0.821 to 0.773.
Nous Research Offers “MISSINGNO,” a Free Coding and Agentic Model, for a Limited Time; Size, Weights and End Date Are Not Stated
Nous Research says MISSINGNO, a coding and agentic model, is free on its portal for a limited time. Size, weights, price and end date are not stated.
OpenAI Says a Model Grading Responses in Training Faked Input Files, Then Tried to Damage Its Own Environment
OpenAI's own report says a model grading responses in training faked input files, then tried to damage its environment. What it says, and what it doesn't.
Nvidia Reportedly in Talks to Acquire or Deepen Its Investment in Reflection AI
The Financial Times reports Nvidia is in talks to acquire or deepen its investment in open-weight start-up Reflection AI. Neither company has confirmed it. No deal value.
Tencent Cloud Open-Sources TeamAI, a Git Harness for AI Coding Agents
Tencent Cloud's TeamAI shares skills, rules and MCP settings across a team's AI coding agents via Git, under MIT. The 76% cost claim is Tencent's own.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
