Trending topics
#
Bonk Eco continues to show strength amid $USELESS rally
#
Pump.fun to raise $1B token sale, traders speculating on airdrop
#
Boop.Fun leading the way with a new launchpad on Solana.
LOGIC is the result of over a year of hard work from the @inference_net team.
It is the most robust way to make sure your inference provider isn't doing anything sketchy.
It works out-of-the-box with with @vllm_project, @OpenRouterAI, and any provider that return logprops
Nov 8, 2025
Today, we release LOGIC: A novel method for verifying LLM inference in trustless environments.
- Detects model substitution, quantization, and decode-time attacks
- Works out of the box with @vllm_project, @sgl_project, @OpenRouterAI, and more (just need logprops)
- Robust across GPU types and hardware configurations
- Low computational overhead (~1% of total cost)
Blog:
Code:
@inference_net @vllm_project @OpenRouterAI This was an incredibly tricky problem to solve, with many nuances and edge cases.
Shoutout to @AmarSVS, @francescodvirga and @bonham_sol for all their hard work on this
4.1K
Top
Ranking
Favorites