Gemini’s Managed Agents Now Run on Free Tier — But the Budget Controls Are Why Devs Should Care
Gemini’s managed agents now run on free tier, but budget controls and scheduled triggers are…
Category: AI Engineering
AI Engineering 354ms to First Audio: Gemma 4 31B on LiveKit Changes the Math for Voice AI
LiveKit now hosts Gemma 4 31B with 354ms time to first audio. This open-weight model…
70B LLMs on 4GB VRAM — AirLLM’s Layer-by-Layer Trick That Rewrites the Rules
AirLLM enables running 70B LLMs on 4GB VRAM without quantization. This open-source library loads transformer…
GPT-Red Breaks Every Model It Faces — Then Makes the Next One Unbreakable
OpenAI’s GPT-Red breaks every model it faces, then uses those attacks to train GPT-5.6 Sol…
AI Engineering Tencent’s Hyra Beats Human-Optimized Benchmarks — and Outperforms Claude Code Along the Way
Tencent’s Hyra beats human-optimized benchmarks and outperforms Claude Code in 3D modeling. Learn how this…