How IT teams use AI, how to do it well, and what it means for your job. Written for people who keep the systems and laptops working, not people who build models.
Sage-A1.5 is a 35B MoE agentic model from Shanghai AI Lab. See GAIA, BrowseComp and SWE-bench Pro scores against larger models, plus SGLang and vLLM serving.
Raon-1 mini preview is KRAFTON AI's Apache 2.0 30B-A4B MoE with hybrid attention and 262K context. Specs, NVFP4 on a 32GB RTX 5090, and benchmarks.
Fish Audio Drama 3 is an open-weight MoE text-to-speech model. Here are the VRAM needs, the 4-bit quant, bracket directions, and how it ranks.
How Calif researchers used OpenAI and Gemini models plus a reusable skill file to turn a PHP out-of-memory bug into WordPress RCE, and what it means.
Two critical PHP flaws, found with AI help, led the NSA and Japan to urge patching or taking sites offline. Here is what happened and who is exposed.
DeepSeek Recipe keeps user-typed control markers as plain text, blocking a classic injection trick. Here is how the failure works and how to test it yourself.
Temperature 0 isn't always deterministic. Batch composition changes GPU math and flips tokens. Here's why, and when to use batch-invariant inference.
Buying a Mac mini to run AI agents all day? Here is how to size RAM and storage, what local models change, and why a bigger machine won't fix agent bloat.
Ornith-1.5-122B posts 76.9 on SWE-bench Pro and 84.5 on Verified. Here is how it compares with Qwen3.8, Nemotron 3.5 Super VL, DeepSeek-V4-Flash and Beam.
Tencent's Hy-Memory-30B-A3B memory writer averages 55.49 across four harnesses vs Claude Opus 5 at 54.62. Per-harness and per-benchmark scores inside.
Spark-X2.6-4B claims best-in-class small-model results and efficiency on par with Qwen3.5-4B and Gemma-E4B. What the card says and what it leaves out.
Run Ornith-1.5-122B locally: llama.cpp GGUF setup, VRAM and context trade-offs, runtime versions to check, and how to handle thinking-mode output.
DeepSeek-V4.1-Flash-1017 gains 11.1 points on Terminal-Bench 4.0 over V4.1-Flash. See how it stacks up against Opus 5, GPT-5.6 Sol, GLM-5.3 and K3.
Serve Tencent's Hy-Memory-30B-A3B with vLLM as hy-memory, call it via the OpenAI-compatible API, and use it as the write path in Mem0 or MemOS.
Run Spark-X2.6-4B, an Apache 2.0 4B on-device agent model with 1M-token context, via Ollama, llama.cpp, LM Studio, MLX, vLLM or SGLang.
Run NVIDIA Dory1.0-4B locally with vLLM or llama.cpp on Apple Silicon, choose 1, 2 or 4 loops, and cut KV cache memory with last-loop caching.
DeepSeek-V4.1-Flash-1017 ships MIT-licensed with no Jinja template. See sampling settings, 1M context, the encoding folder and deepseek-recipe.
NVIDIA's open-weight Nemotron 3.5 Super VL uses Mamba-2, MoE and attention with 120B total, 12B active parameters and 1M context. Here is where it fits.
Enable developer mode on an LG or Android TV, find its IP, and point Hermes agent at a local Qwen model in Ollama to manage settings with an undo list.
Hands-on results for NVIDIA's open Nemotron 3.5 Super VL (120B, 12B active): bug fixing, vision, translation, circuits, and benchmarks.
Microsoft Agent 365 and Project Perception give agents their own identity, time-bound permissions and risk-based access. Here is how the pieces fit.
Ornith-1.5-122B tested on a Docker bug fix, vision, screenshot reasoning, creative HTML and 80-language translation. Here is where it held up and failed.
Should you build internal tools with AI or keep buying SaaS? See which categories to build now, which to keep buying, and what the data says.
Compare per-agent helpdesk SaaS pricing from Zendesk and Freshdesk with building an internal ticketing tool on Cloudflare Workers and D1 for about $5 a month.