A model ID is not an agent. Protocol, tool contracts, context recovery, and acceptance determine how much capability becomes reliable work.
Same DeepSeek V4 Flash, Different Agent: Why the Runtime Changes the Result
Related
Further Optimizing the Vision-Only Harness: the Notes Rule
A short follow-up to I replicated the vision-only Pokémon run Anthropic showcased on the Fable 5...
Speech-to-Text APIs in 2026: What the Pricing Pages Don't Tell You
I ran a 9-second WAV file through faster-whisper on a CPU with no GPU and no API key. It took 0.6...
Your agent doesn't need more tools, it needs better tool descriptions
Most agent failures I've debugged weren't reasoning failures. The model reasoned fine. It just picked...