Policy & Regulation

Open models have real benefits. Do they outweigh the risks?

MIT Technology Review examines the debate over open versus closed AI models, weighing the benefits of democratized access and preventing power concentration against safety risks including misuse for hacking and other harmful applications. The article explores middle-ground approaches such as tamper-resistant models and staged releases that attempt to balance safety concerns with the imperative to prevent AI capability concentration among a small number of companies.

Source: MIT Technology Review

Securing the agentic enterprise with data lineage

The article discusses security challenges in agentic AI systems, highlighting how data moves across multiple agents and sources without proper tracking, leading to potential exposure of sensitive information. It argues that enterprises deploying agentic AI need data lineage capabilities to maintain governance, accountability, and trust in hybrid human-agent workflows.

Accelerating engineering for the physical world

ChatGPT and Codex are being applied to accelerate engineering workflows including computer-aided design, printed circuit board design, and simulation tools. The article discusses how large language models are improving productivity in physical engineering disciplines. Source: OpenAI

How Cisco defends at machine speed with OpenAI

Cisco has integrated OpenAI models with its network intelligence capabilities to enhance enterprise security defenses. The integration aims to create more adaptive security systems that can operate at machine speed. Source: OpenAI

Anthropic is working on a system to prove AI models’ identity

Anthropic is developing FlashProve, a verification system that enables users to authenticate whether AI responses genuinely originate from the claimed model. The system addresses concerns about AI impersonation and misrepresentation by providing cryptographic proof of model identity. Source: TechCrunch

Read more

Securing the agentic enterprise with data lineage

Accelerating engineering for the physical world

How Cisco defends at machine speed with OpenAI

Anthropic is working on a system to prove AI models’ identity