llama.cppOct 17, 2026Releases
b11709OpenRouterOct 17, 2026New Models
New model: Elorian: GlimpseOpenRouterOct 16, 2026New Models
New model: Reflection: Beam 1.0 501B A23BVercelOct 16, 2026News
Elorian AI's Glimpse now available on AI GatewayarXiv cs.CLOct 15, 2026Research
Training Reasoning Models to Generate Diverse Scientific IdeasVercelOct 15, 2026News
Muse Spark Open now available on AI GatewayVercelOct 15, 2026News
Cat Jam is now available in stealth for free on AI GatewayarXiv cs.CLOct 14, 2026Research
VASPO: Self-Distillation with Privileged Value EstimationarXiv cs.CLOct 13, 2026Research
DoubtLess: Training-Free Contrastive Decoding for Efficient ReasoningOpenRouterOct 13, 2026New Models
New model: LiquidAI: LFM2.5-24B-A2BOpenRouterOct 13, 2026New Models
New model: Google: Gemini 4 ArgonLiquid AIOct 13, 2026News
LFM2.5-24B-A2B: Built for Fast On-Device AgentsGoogle for DevelopersOct 13, 2026News
Gemini 4 Argon for RoboticsOpenRouterOct 12, 2026New Models
New model: Meta: Muse WonderNo Priors · YouTubeOct 9, 2026Watch
Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha LaskinNo Priors · YouTubeOct 9, 2026Watch
Beam: The Great American Open Model with ReflectionAI Co-Founder and CEO Misha LaskinVercelOct 7, 2026News
Glyph Cluster is now available in stealth for free on AI GatewayTimothy B. Lee (Understanding AI)Oct 5, 2026Columns
Why agent swarms could be the next “scaling law”arXiv cs.AIOct 2, 2026Research
Reasoning Models Are Accurate but Unsound on IdentificationarXiv cs.LGOct 1, 2026Research
On Language Drift during RLVR Post-Training