Hermit permite a los desarrolladores adaptar agentes de IA a nuevas tareas sin necesidad de ajustar modelos ni bifurcar el código, optimizando así los flujos de trabajo de desarrollo.
Resumen generado con IA. Consulta el original para comprobar el contexto y la precisión.
Este es el extracto disponible del feed. Puede estar abreviado o en el idioma original.
Infini-AI-Lab has released Hermit, an open-source harness adapter framework for AI agents. Hermit is a framework from Infini-AI-Lab that trains an external ‘harness adapter’ while the agent’s model and harness stay frozen. The first release, v0.1.0, shipped on October 25, 2026. CMU postdoc Haizhong Zheng announced it on X on October 27. For developers, the pitch is simple: adapt Codex or Claude Code agents to new tasks without fine-tuning or forking the harness. TL;DR Footprint: A Python framework. No parameters of its own. Apache-2.0, pip install hermit-harness. Runs on: The offline Quick Start needs no GPU, model account or dataset. Real runs use any API backend or a local vLLM, SGLang or Ollama server. Performance: Reported gains over no-adapter baselines on OfficeQA, CL-Bench and ServeLearnBench, all with GLM 5.3 Flash. Best: MWM adapter hits 0.795 accuracy on CL-Bench database exploration, vs 0.580 for the in-context baseline. Worst: The prompt-only adapter scores 0.470 on the same venue, below that 0.580 baseline. Bottom line: Best: one training loop for 5 harness evolution methods. Worst: most results are single runs, self-reported. What is a harness adapter? A harness adapter is a trainable external harness. It works like a plugin with training support built in. A model adapter, such as LoRA, adapts a model. A harness adapter adapts an existing agent instead. The adapter can hold instructions, skills, memory, tools, executable code and agent coordination logic. It can even be a whole repository. Its specification says which parts are learnable and how updates get checked. The base model and harness never change. The team gives 3 reasons for this design. Many harnesses are closed-source. Editing open ones can break carefully tuned component interactions. And a learned adapter can move between compatible models and harnesses. How does Hermit train an adapter? Hermit uses an RL-style training loop. A Trainer runs a batch of tasks through the acting
Una ayuda automática para ordenar, basada en fuentes, palabras clave y entidades, en una escala de 1–12. Alta: 9–12; media: 6–8; baja: 1–5. No mide urgencia, verifica noticias ni representa respaldo editorial.
El nuevo modelo de voz de Block, entrenado exclusivamente con audio y sin texto, ofrece una alternativa más rápida y natural a los agentes de voz basados en texto actuales.
La nueva API de TTS de AssemblyAI, con un costo de 15 USD por millón de caracteres, ofrece una síntesis de voz asequible y de baja latencia para agentes telefónicos en vivo, simplificando el desarrollo al unificar la conversión de voz a texto y de texto a voz bajo un solo proveedor.
El modelo abierto Nemotron 3.5 Transcribe de NVIDIA integra la transcripción de voz a texto, la identificación de hablantes y la traducción en un único modelo eficiente, simplificando el procesamiento de audio multilingüe para los desarrolladores.