Notes from the trenches on AI engineering, LLM apps, and the full-stack work that holds it all together.
Google DeepMind shipped Gemini 3.6 Flash, 3.5 Flash-Lite, and a cyber-specialist 3.5 Flash Cyber inside CodeMender. Defenders get a limited pilot; builders should note the dual-use deployment model.
Claude Fable 5, GPT-5.6 Sol, Kimi K3, and AxiomProver all reported perfect IMO 2026 scores. The interesting part is cost, grading tier, and what happens when benchmarks stop separating models.
Meta renamed llama-recipes to Llama Cookbook with notebooks for inference, LoRA fine-tuning, RAG, and end-to-end use cases. Here is how I would navigate it for a client MVP.
Cursor v3.11 adds durable side chats via /side and /btw, a local index for Cmd+K transcript search, and five new cloud agent hooks. Here is how I use parallel threads without losing the main agent.
Google AI Studio Build mode now assigns custom subdomains under ai.studio at publish time. Here is when the free URL is enough, when you still need your own domain, and the gotchas around unpublishing.
OpenAI attributed a proof of the Cycle Double Cover conjecture to GPT-5.6 Sol Ultra, 64 parallel subagents, and a Lean 4 formalization in openai/cdc-lean. Here is what the result means before peer review lands.
Unsloth shipped dynamic NVFP4 Qwen3.6 checkpoints on July 10 that beat NVIDIA's own NVFP4 on throughput while holding benchmark accuracy. Here is the backend choice that makes or breaks the speedup.
Qualifying open-source maintainers can apply for six months of Claude Max 20x ($1,200 value) with priority access, Claude Code, and roughly 900 messages per session window. API access is not included.