Anthropic releases FlashProve inference verification prototype
What happened
On 4 November 2026, Anthropic released FlashProve, an open-source research prototype that uses zkSNARKs to generate cryptographic proofs for model outputs, verifying that a response really came from the model it claims to, without exposing model weights. According to the technical report, on a single H100 it generates proofs for the 400B-parameter Llama 4 Maverick at about 110 tokens per second, each proof is about 19MB, verification on a standard CPU takes 17 seconds, and the overhead is roughly 70x to 95x compared with ordinary inference. The prototype is at the research stage, with no further application progress disclosed.
Written by AI from the reports · updated 2 h ago
Timeline
Follow the reports to see the event from each side.
- The DecoderAnthropic's new prototype proves which model wrote an AI response without exposing its weights
Anthropic has released FlashProve, a research prototype that uses cryptography to verify whether an AI response actually came from the claimed model. The system still has significant limitations.
Heat of this event
Current heat 9·Peak in the comparable range 10（Nov 5 01:00）·Change over 24 hours in the comparable range –
The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.