Avkash K(@avkashk):Turns out the model isn't the product. The harness matters almost as much. Same model. Different harness. Different performance, different cost, different outcome. We may be benchmarking “models” when we should actually be benchmarking the entire agent stack.

Avkash K

@avkashk

Co-Founder @fencio_dev. Building the Adaptive Zero-Trust Firewall for AI Agents.

加入 April 2010

3.9K 正在关注 1.7K 粉丝

Avkash K@avkashk

2026.09.17 16:33

Turns out the model isn't the product. The harness matters almost as much. Same model. Different harness. Different performance, different cost, different outcome. We may be benchmarking “models” when we should actually be benchmarking the entire agent stack.

显示更多