Llama 4 Scout 17B 16E Instruct: added a reported Ollama infrastructure exploit, distinguished from a Scout-specific model vulnerability

The OnAirToday AI Progress Tracker recorded a verified change to Meta AI's Llama 4 Scout 17B 16E Instruct (version Llama-4-Scout-17B-16E-Instruct): Added a reported Ollama infrastructure exploit, distinguished from a Scout-specific model vulnerability.

Meta's Llama 4 Scout is an instruction-tuned, text-and-image model with 109 billion total parameters, 17 billion active parameters per token, and 16 experts. Its documented context window is 10 million tokens, with downloadable weights governed by the Llama 4 Community License and deployment limits that depend on hardware and serving configuration.

What changed in this review:

• Capability score 47 → 66
• Flaws and limitations updated

Anyone building on Llama 4 Scout 17B 16E Instruct should re-check the model's risk dashboard before shipping, since flaws and reported incidents are what moved in this review.

The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/llama-4-scout-17b-16e-instruct.

References:

• https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct
• https://ai.meta.com/blog/llama-4-multimodal-intelligence/
• https://www.darkreading.com/cyber-risk/nemo-claw-networking-llm-poisoning-openclaw