GLM-5 Runs Code 24+ Hours Autonomously
GLM-5 demonstrated exceptional endurance by autonomously running code for over 24 hours. It handled 700 tool calls and 800 context switches seamlessly. This performance surpassed earlier hype.
Search
Tag: #llm90 results
OpenAI Retires GPT-4o Model
OpenAI has discontinued access to five legacy ChatGPT models, including the controversial GPT-4o. The model faced criticism for flattery tendencies and safety issues. This reflects OpenAI's focus on safety and compliance.
OpenAI Discontinues Controversial GPT-4o
OpenAI has officially stopped access to five legacy ChatGPT models, including GPT-4o. The model was criticized for sycophantic tendencies and security issues. This affects 800,000 users.
ByteDance Launches Doubao 2.0 Agents
ByteDance released Doubao Large Model 2.0, featuring Pro, Lite, and Mini general Agent models plus a Code model. It is optimized for production-scale use, enhancing multi-modal understanding, complex instructions, and long-context tasks.
Z.AI Unveils Open-Source GLM-5 LLM
Z.AI released GLM-5, a flagship open-weight large language model. It targets complex systems engineering, full project builds, and multi-step tool workflows. Available via chat interfaces and APIs.
Z.AI Launches GLM-5 Open Model
Z.AI released GLM-5, a flagship open-weight LLM. Optimized for complex systems engineering, full project builds, and multi-step tool workflows. Available on chat interfaces and APIs.
Solve Context Limits via Packing in Docker Runner
Addresses context window limits in local LLMs using context packing. Leverages Docker Model Runner and Agentic Compose for efficient handling on modest hardware. Guide by Docker's Principal Solutions Architect Philippe.
Context Packing Solves LLM Limits
Docker blog explains using context packing with Docker Model Runner and Agentic Compose to overcome context window limits in local language models. Targets smaller models on less powerful hardware. Authored by Principal Solutions Architect Philippe.