Fetching from the wire…
01
02
03
04
05
06
07
08
Security2026-09-25 · source-backed
arXiv 2609.29757 ran Ollure, a honeypot emulating the Ollama API with no model behind it, across four cloud and university deployments. Most traffic was discovery, fingerprinting and model enumeration, but it also caught model-management abuse, path traversal and SSRF probes, RCE payloads, crypto miners, resource exhaustion, prompt injection and agent-style tool use. Port 11434 exposed publicly gets found by automated scanners, and now there's a number attached to how fast.
Each link below shares sources, entities, or timing with this story.
Ollama cut v0.34.0-rc1 on September 5 at 23:49 UTC, and the headline item changes the shape of the local-versus-hosted decision rather than the performance of either side: Ollama-hosted open models can be selected directly inside ChatGPT Desktop, with setup driven from the Oll...
The July 6 release delivers nearly 90% faster Gemma 4 token generation through multi-token prediction with automatic draft-length tuning, on by default, output-preserving, no config (Ollama). It also adds MLX-engine support for more model families and flash attention for older...
Released September 14, it graduates MLX safetensors ollama create out of experimental, while GGUF creation now requires llama.cpp tooling for conversion and quantization. Runaway repeat-token detection now needs 100 repeated tokens before firing, cutting false positives on OCR...
The models are good. The license is the real story. Google released Gemma 4 on April 2 with four variants: E2B, E4B, 26B MoE, and 31B Dense. All built on the Gemini 3 architecture. The 31B Dense variant claimed #3 on Arena AI's text leaderboard, beating models 20x its size. Th...
AlexsJones/llmfit released v1.1.10 today, adding RamaLama runtime discovery to its MCP server, the Qwen3.8 model family and MiniMax M3 vision capability exposure (GitHub). It also merged 32 MLX benchmark results on an Apple M4 Pro, the project's first MLX entries, giving an ap...
Alibaba released Qwen3.6-27B on April 22. Dense architecture. Open weights. 77.2% on SWE-bench Verified, within 3.7 points of Claude Opus 4.6. On SkillsBench, it scores 48.2% versus its own 397B MoE predecessor's 30.0%. That's a 77% improvement with 14.8x fewer parameters. Let...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.