HomeTagsReinforcement learning

reinforcement learning - Page 11

Stories from reinforcement learning come first, newest first, then stories from connected topics (LLM post-training, AI Models, coding agents, Benchmarks, AI, Open Source), each labelled with where it comes from. This view is not indexed by search engines.

Latest

MOSS-Live Links Full-Duplex Voice, Vision and Background Tasks

MOSS-Live combines full-duplex speech, live vision and background tools. OpenMOSS’s own tests show strengths in interaction, but mixed task results.

Nous Releases Arete-27B to Alter Qwen’s Political Framing

Nous releases Arete-27B, a Qwen3.8-27B fine-tune targeting Chinese-state framing. Its bias and capability results come from Nous’s own tests.

AMD Open-Sources PrimusClaw Runtime for GPU Agent Sessions

PrimusClaw runs agent sessions and sandboxes on Kubernetes beside AMD Instinct GPUs. AMD reports internal usage, not an independent benchmark.

UChicago Wins $10m Laude Grant for AI Weather Almanac

AI weather Almanac aims to help agencies adapt local forecasts, backed by a $10m UChicago lab grant. Reported farmer reach concerns earlier work.

OpenRouter Launches Auto Code and Rebuilds Its Auto Router

OpenRouter Auto Code selects models for coding agents. The company reports lower cost per task in five benchmarks; model usage is still charged.

FMF Jailbreak Rating Framework Opens for Comment to 21 Dec

FMF Jailbreak Rating Framework v1.0 rates cyber jailbreaks on four dimensions. Voluntary; comment open to 21 Dec 2026. Not law or certification.

Carta Evergreen Opens Multiplayer AI Coding for Teams

Carta Evergreen: multiplayer AI coding with agents; Carta cites ~20k PRs/week and lower reverts. Usage fees: $0.15/M tokens plus provider price.

Cognition Says Devin Review 2.0 Cuts PR Review Cost 82%

Devin Review 2.0: Cognition says PR review cost down 82% since August; typical $0.25–$0.75. Company metrics, not independent benchmarks.

OpenAI Launches GPT-6 Cyber for Defensive Research

GPT-6 Cyber: OpenAI says its cyber model scores 48.5% on ExploitGym and helped produce 948 Linux LPE exploits in a controlled research pipeline.

Google Makes Gemini Omni 1.2 Flash Generally Available

Gemini Omni 1.2 Flash is generally available: native 15s video, $0.07/s at 720p (30% less than 1.1), multi-turn editing, SynthID.

Latest on TSN

Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.