Cognition released the Devin Vulnerability Fixes plugin, 3 MIT-licensed agent skills that inventory, patch and test PHP, Node.js and self-managed GitLab…
Tag: MarkTechPost
How to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling Guide
Explore a complete coding guide comparing Underdog Saluki 27B with ISTA’s GSQ-RCO quantization, examining GGUF headers, memory usage, and BFCL…
Meet Anthropic’s sandbox-runtime: OS-Level Sandboxing for AI Agents, No Containers
Anthropic sandbox-runtime (srt) is the open-source, OS-level sandbox behind Claude Code. It restricts file and network access for agents, MCP servers and…
Stateful Agentic Engineering Copilots with Letta: Core Memory, Shared State, Semantic Retrieval, Custom Tools, Streaming, and Portable Agent Workflows
Discover how to extend agentic memory beyond basic prompts by building a stateful engineering copilot with Letta. This comprehensive guide covers…
NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots
NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B for local voice assistants, game characters and…
Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms
Kyutai released CADRE, a family of 7 open causal diffusion video autoencoders for interactive world models. World models built on CADRE run at 20 fps on 1…
Moonshot AI Releases Kimi K3.1 Pro: A 2.8T Total/104B Active Params (MoE) Model with 1M Context
Moonshot AI released Kimi K3.1 Pro, a 2.8T-parameter, 104B-active MoE model with 1M-token context. It scores 65.7% on Terminal-Bench 4.0, costs $2/$10 per…
IBM AI Releases Granite Speech 5.0 2B for Multilingual Transcription and Translation
IBM released Granite Speech 5.0 2B, an Apache 2.0 speech recognition and translation model. It ranks #2 on the Open ASR Leaderboard with 5.68% average…
Perplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Student Reinforcement Learning Method
Perplexity and NVIDIA introduced JOLT, a post-training method that trains one model as both teacher and student. On MATH it matched GRPO’s accuracy with…
A Coding Guide to Cactus Whistle: Does a 16.9 MB Speech Model Hold Up Against Whisper Base? Word Error Rate, Speed, Streaming, Timestamps, Keywords, and Speech-to-Tool Calls on a CPU
Explore a comprehensive coding guide benchmarking Cactus Compute’s 16.9 MB speech model against Whisper base. Learn about word error rates, CPU speed,…