Agent Safety Gaps, Memory Learning, and Leaner Inference
Three new papers expose how production agent frameworks fail under attack, why RLVR training discards useful cross-episode signals, and how calibrated confidence cuts inference compute by 12x.
Articles Tagged "Inference"
d-Matrix Corsair - In-Memory Inference Accelerator
d-Matrix Corsair is an SRAM-based in-memory compute ASIC in production since June 2026, targeting 10x faster and 5x more power-efficient LLM inference vs GPU baselines.
OpenAI Jalapeño - Custom LLM Inference ASIC
OpenAI's first custom AI chip, co-designed with Broadcom on TSMC 3nm, targeting 50% lower inference cost than GPU alternatives.
Agent Languages, Sampling Ceilings, and Abstention
Three new papers on agents inventing symbolic languages to cut reasoning tokens by 3-6x, sampling ceilings that waste inference compute, and context-engineering to double agentic abstention rates.
Claude Sonnet 5 Is Anthropic's New Agentic Default
Anthropic's Claude Sonnet 5 becomes the default model across all plans, promising near-Opus agentic performance at a third less than Sonnet 4.6's standard price.
Cline's $10 Plan Bundles Ten Open-Weight Coders
ClinePass gives developers access to ten curated open-weight coding models for $9.99 a month, betting the agent harness matters more than the model.
Quantization's Hidden Tax, Cliff Tokens, Smarter Memory
Three new arXiv papers reveal hidden costs in quantized reasoning models, single-token failure triggers, and a new framework that cuts agent memory errors by up to 79%.
Best LLM Gateways 2026 - LiteLLM, Portkey, and 5 More
A hands-on comparison of seven LLM gateway and routing tools - LiteLLM, Portkey, Helicone, OpenRouter, Martian, Cloudflare AI Gateway, and Bifrost.
DiffusionGemma 26B Review: 4x Faster, Real Tradeoffs
Google DeepMind's DiffusionGemma generates 1,000+ tokens per second through parallel diffusion, trading 5-19 benchmark points against Gemma 4 for speed and unique bidirectional generation capabilities.
Amazon Eyes Third-Party Trainium Sales to Rival Nvidia
Amazon CEO Andy Jassy hints the company will sell Trainium3 racks directly to outside data centers, citing a potential $50B revenue run rate and sold-out chip supply.
Baseten Closes $1.5B Round as Open-Source AI Matures
Baseten's $1.5B raise at a $13B valuation signals a structural shift as open-source models displace closed APIs in enterprise AI.
Voxtral TTS
Mistral's first open-weight text-to-speech model: 4B parameters, 70ms latency, voice cloning from 3 seconds of audio, and a 68.4% win rate over ElevenLabs Flash v2.5 in blind tests.
