Next up on First Pass: A conversation with @lorenc_dan from @chainguard_dev
We had one of the worst weeks ever in new security vulnerabilities discovered. What does the PHP vulnerability mean, how can companies prepare, what should we expect in the future, etc
We dig in!
ALERT🚨: In less than 20 days, AMD MI355X @vllm_project performance on MiniMax M3.1 Flash has increased by 4x! This is achieved using the new @Inferact AMD kernels written in FlyDSL, which are deterministic, meaning they never use atomic adds to accumulate their outputs.
Great work by @vllm_project, @Inferact, and @AnushElangovan on this amazing achievement!
1/ Today we’re publishing the Databricks AI Index, showing trends from enterprises who manage AI with our Unity Gateway. Data covers >10,000 companies with broad representation (Digital Natives, Fortune 500, Global 2000, etc...). Enterprise AI consumption is changing quite a bit:
Anthropic new models out today - Fable 5.2 and Mythos 5.2
Fable 5.2 available today at $8 per million input tokens and $40 per million output tokens
Seeing a reduction in frontier pricing!
Awesome to see @ClickHouseDB continue to push the product frontier.
- Deeper into OLTP
- Deeper into natural applications built on top of Clickhouse (Observability and Security / SIEM)
- Deeper into the AI gateway space
Tired of seeing benchmarks saying we are at AGI but models still can't understand a 3D protein view or a floor plan? When a visual model gets something wrong, is it failing to see or failing to reason about what it sees?
We've built two benchmarks that answers these questions. Explore DecoyCount and ScienceVision here: github.com/elorian-ai/decoyc… and huggingface.co/datasets/Unip…
And thank you @mercor and @UniPat_AI for your partnership in building these!
Inferact now serves more than 7 trillion tokens a day.
That traffic runs on the Inferact Platform, which serves frontier models with optimized vLLM across heterogeneous hardware and diverse workloads. For context, OpenRouter averaged 19 trillion tokens a day of open-weight traffic over the past 30 days, across all of its providers.
The platform improves through a data flywheel. Production traffic shows us where to improve vLLM, partnerships with accelerators like NVIDIA, AMD, and Google bring those improvements to new hardware, and partnerships with model labs like MiniMax and Kimi bring them to new models from launch day.
Next, we’re automating that flywheel with agents that find and validate optimizations on their own, so the platform improves with every token it serves.
inferact.ai/news/7-trillion-…
Next up on First Pass - a conversation with Arya (@a_a) from @SierraPlatform on their Personal Agent Protocol
Personal agents are taking over, and we need more streamlined ways for the services / products / websites we use to interact with personal agents
Provable inference is coming. A very real commercial use case for zero knowledge proofs is forming!
"Recently commercial efforts have reached impressive numbers, with Attestable proving Gemma 4 31B at 53–77 tok/s on a single H100"
cc @attestableanthropic.com/research/prova…