All tags
Topic: "agent-reliability"
not much happened today
qwen-3.5-0.8b qwen-3.5-2b qwen-3.5-4b qwen-3.5-9b codex-5.3 claude-3 alibaba ollama lm-studio openai anthropic multimodality reinforcement-learning long-context hybrid-attention on-device-ai model-deployment agent-reliability agent-observability coding-agents benchmarking runtime-optimization token-efficiency nrehiew_ kimmonismus lioronai danielhanchen theo htihle teortaxestex theprimeagen yuchenj_uw _lewtun saen_dev _philschmid omarsar0
Alibaba released the Qwen 3.5 series with models ranging from 0.8B to 9B parameters, featuring native multimodality, scaled reinforcement learning, and targeting edge and lightweight agent deployments. The models support very long context windows up to 262K tokens (extendable to 1M) and use a novel Gated DeltaNet hybrid attention architecture combining linear and full attention layers. Deployment examples include Ollama and LM Studio, with a notable 6-bit on-device demo on iPhone 17 Pro. Evaluators are cautioned that reasoning is disabled by default on smaller models. In coding agents, Codex 5.3 shows promising benchmark results on WeirdML with 79.3% accuracy, though availability and downtime remain critical challenges, especially highlighted by Claude outages. Agent reliability and observability are emphasized as cross-functional problems requiring clear success criteria and practical evaluation strategies. Studies show that using AGENTS.md and SKILL.md guardrails can significantly reduce runtime and token usage by mitigating worst-case thrashing in coding workflows.
AI Engineer World's Fair: Second Run, Twice The Fun
gemini-2.5-pro google-deepmind waymo tesla anthropic braintrust retrieval-augmentation graph-databases recommendation-systems software-engineering-agents agent-reliability reinforcement-learning voice image-generation video-generation infrastructure security evaluation ai-leadership enterprise-ai mcp tiny-teams product-management design-engineering robotics foundation-models coding web-development demishassabis
The 2025 AI Engineer World's Fair is expanding with 18 tracks covering topics like Retrieval + Search, GraphRAG, RecSys, SWE-Agents, Agent Reliability, Reasoning + RL, Voice AI, Generative Media, Infrastructure, Security, and Evals. New focuses include MCP, Tiny Teams, Product Management, Design Engineering, and Robotics and Autonomy featuring foundation models from Waymo, Tesla, and Google. The event highlights the growing importance of AI Architects and enterprise AI leadership. Additionally, Demis Hassabis announced the Gemini 2.5 Pro Preview 'I/O edition', which leads coding and web development benchmarks on LMArena.