TinyFish's agentic search architecture runs 7 phases; Search and Fetch scored 79.0% grounded completion at $0.050 per task.
TinyFish published two engineering research articles on agentic search. One defines a 7-phase production architecture with evidence contracts and bounded retries. The other explains why its deep ...
Google Cloud announced Agent Compute Engine, a compute service that gives every AI agent its own hardware-isolated microVM with no credentials inside. It already runs Gemini agents and enters preview ...
Liquid AI just announced Liquid RIPL, short for Real-time Inference Pipeline. RIPL is a low-latency engine that serves Liquid ...
Gradium Phonon is a 31M-parameter on-device TTS model under Apache 2.0, reporting 1.70% WER on hard English sentences.
Cohere Rerank 5 adds Pro and Fast rerankers, Context Focus passage extraction, calibrated scores, and 82.2 on BRIGHT.
IBM Granite Speech 5.0 2B, an Apache 2.0 ASR model, ranks #2 on Open ASR Leaderboard at 5.68%. IBM speech recognition model ...
Google Agent Compute Engine gives AI agents hardware-isolated microVMs with zero credentials inside, previewing in the coming ...
You.com Inference Router serves 12 open-weight models through 1 OpenAI-compatible API with 99.9% uptime SLA and zero retention.
Introduction Teams shipping AI agents at scale keep running into the same pattern. Even agents built on top-tier models like ...
Gradium has open-sourced Phonon, a family of on-device text-to-speech models. The English Phonon 31m ships under Apache 2.0, fits in 64.5 MB, and starts speaking in about 7 ms on a laptop CPU.
Recursive Flint is a 40B MoE local coding model with 2.5B active parameters, scoring 74.2% on SWE-bench Verified.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results