Skip to main content

AI

IBM details training of Granite 4.2 reasoning models

IBM details training of Granite 4.2 reasoning models

Thinking, then acting
Authors: Granite Team, IBM Overview Granite 4.2 is IBM's first family of dense, decoder-only reasoning LLMs, released in three sizes: 3B, 8B, and 30B. These models are post-trained from Granite-4.1 b…
Gemini 4 Argon helps builders create 3D worlds

Gemini 4 Argon helps builders create 3D worlds

Imagination, compiled
Google's new frontier model, Gemini 4 Argon, is designed for deep work on complex tasks in coding, finance, legal, cybersecurity, and science. Google says its depth and precision across multi-step ta…
Database-checked rewards lifted 27B agent's dependable tasks 2.8x

Database-checked rewards lifted 27B agent's dependable tasks 2.8x

Skill, Not Luck
Microsoft and Hugging Face's ThinkingBox-Training, now on GitHub, uses the same executable database checks that grade agents as training rewards. In one run, Qwen3.8-27B's average success rose from 5…
PyTorch 2.15 speeds Mac MoE decoding up to 6.5×

PyTorch 2.15 speeds Mac MoE decoding up to 6.5×

Tokens, unleashed
PyTorch 2.15 brings large speedups and new capabilities to Apple silicon Macs. The release is from the PyTorch team at Hugging Face, which works on the MPS backend to make the Mac a first-class place…