AI Shorts

Auto Added by WPeMatico

ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Tech News, Technology

ByteDance’s Seed team has introduced SeedRealtime, a native audio-visual full-duplex LLM. The model fuses audio, video and text in a single unified architecture. It interacts in real time over continuous multimodal streams, rather than one turn at a time. Seed positions it as a step toward omni-modal interaction, and claims three breakthroughs: joint audio-visual understanding, […]

ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model Read More »

NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplex Speech-to-Speech Model with ~450 ms Turn-Taking and Live Tool Calling

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Audio Language Model, Editors Pick, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Python, Staff, Tech News, Technology, Uncategorized, Voice AI

NVIDIA has released NemotronLabs VoiceChat 11B, an open 11B end-to-end speech-to-speech model for real-time, full-duplex conversation. Instead of chaining ASR, an LLM, and TTS, it performs streaming speech understanding and speech generation in one unified network. That removes the multi-model orchestration and API handoffs a cascaded stack requires, and cuts end-to-end latency: measured smooth turn-taking

NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplex Speech-to-Speech Model with ~450 ms Turn-Taking and Live Tool Calling Read More »

Meet Shepherd: An Open-Source Python Substrate That Lets Meta-Agents Fork, Replay, and Revert Any Agent Run

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Shorts, Applications, Artificial Intelligence, Editors Pick, New Releases, Open Source, Staff, Tech News, Technology

Long-running agents accumulate state that no transcript captures. A coding agent at step 10 holds edited files, a running dev server, installed packages, and a warm prompt cache. When it misreads a traceback and rewrites a file that was already correct, neither available recovery path is cheap: patching forward grows the context and the token

Meet Shepherd: An Open-Source Python Substrate That Lets Meta-Agents Fork, Replay, and Revert Any Agent Run Read More »

Pokee AI Releases Pokee-Isaac 28B: A 10M-Token Context Agentic Model Built to Run Inside the Customer Boundary

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, New Releases, Staff, Tech News, Technology

Long-horizon agents accumulate context faster than they resolve tasks. Every tool output, observation, and intermediate reasoning step stays in the window, and the two capabilities that matter — holding that context and staying coherent across it — have so far been available almost exclusively from cloud endpoints. That excludes regulated industries, public-sector institutions, and on-device

Pokee AI Releases Pokee-Isaac 28B: A 10M-Token Context Agentic Model Built to Run Inside the Customer Boundary Read More »

Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, deep learning, Editors Pick, Enterprise AI, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Security, Software engineering, Staff, Tech News, Technology, Uncategorized

Mistral AI has released Shieldstral 1.0 3B, an open-weights, policy-adaptive multimodal safety classifier that treats content moderation as a single yes/no question rather than a fixed taxonomy of harm categories. Most guardrail models bake their category list into the weights, so re-targeting one to a new deployment context means retraining — and the same content

Mistral AI Releases Shieldstral 1.0 3B: An Open-Weights Policy-Adaptive Multimodal Safety Classifier Matching Models 7× Its Size Read More »

Tencent Cloud Open-Sources TencentDB Agent Memory v2.0: A Team-Level Memory Hub for AI Coding Agents

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

Tencent Cloud has open-sourced TencentDB Agent Memory v2.0, a team-level memory hub for AI agents. The idea is super simple: if project context was already explained once, a new session should not need it repeated. The system turns conversations, documents and code into four reusable memory assets — Chat Memory, Skill, LLM-Wiki and Code-Graph —

Tencent Cloud Open-Sources TencentDB Agent Memory v2.0: A Team-Level Memory Hub for AI Coding Agents Read More »

Microsoft Open Sources code-testing-generator: a Polyglot Unit-Test Agent That Hits 92.1% Task Completion Versus 78.9% for Stock Copilot

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Shorts, Applications, Artificial Intelligence, Editors Pick, model context protocol, New Releases, Open Source, Software engineering, Staff, Stock Market, Tech News, Technology

Microsoft has open sourced code-testing-generator, a polyglot agent that writes unit tests and then proves they work. It ships in the dotnet-test plugin inside the MIT-licensed dotnet/skills repository. The agent targets a gap that coding assistants usually leave open. A prompt like ‘generate unit tests’ does not say which framework, file location or assertions to

Microsoft Open Sources code-testing-generator: a Polyglot Unit-Test Agent That Hits 92.1% Task Completion Versus 78.9% for Stock Copilot Read More »

Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, Language Model, Large Language Model, New Releases, Staff, Tech News, Technology

Liquid AI released LFM2.5-2.6B, an agentic model that runs entirely on-device. It plans, calls tools, and works through multi-step tasks on phones, laptops, PCs, and robots. The model has 2.69B total parameters, a 131,072-token context window, and a 128,000-token vocabulary. Pre-training used approximately 34 trillion tokens. Two checkpoints shipped: LFM2.5-2.6B-Base for fine-tuning, and LFM2.5-2.6B post-trained

Liquid AI Releases LFM2.5-2.6B: An On-Device Agentic Model With 128K Context, Tool Calling, And Open Weights Read More »

Cloudflare Introduces Kitesurf: An Agent-First Web Browser That Runs Entirely in V8 Isolates on Cloudflare Workers

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, New Releases, Software engineering, Staff, Tech News, Technology

Cloudflare has released Kitesurf, a stateless web browser built specifically for AI agents. It runs entirely in V8 isolates on Cloudflare Workers, with no Chromium underneath. Browser engines like Chromium were built for humans, and their memory and compute overhead makes one-browser-per-agent prohibitively expensive. Agents do not need tabs, extensions, or pixel-perfect 60-fps rendering. They

Cloudflare Introduces Kitesurf: An Agent-First Web Browser That Runs Entirely in V8 Isolates on Cloudflare Workers Read More »

Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, New Releases, Open Source, Software engineering, Staff, Tech News, Technology, Uncategorized

Prime Intellect has open-sourced Prime Agent, a self-improving coding harness designed around two abstractions, the Recursive Language Model (RLM) and Continual Harness. Fixed tool schemas and context compaction force a model to work around its own scaffolding. Prime Agent replaces both with a persistent Python REPL and a rewritable harness. With Opus 5, it reports

Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel Read More »