Baseten vs Red Hat

New in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and More

LangChain announced a wave of new LangSmith capabilities at Interrupt NYC, centered on LangSmith Engine v2, Managed Deep Agents v0.8, Trajectories, Fine-Tuning, and Custom Apps. Engine v2 adds red teaming, broader issue detection, and automated fix validation. Managed Deep Agents introduces identity-scoped auth and memory, expanded channels, and built-in web search. LangSmith Fine-Tuning turns agent trajectories into training data for open models, while Custom Apps lets teams build tailored interfaces on LangSmith data.

• LangChain announced the updates on September 25, 2026, at Interrupt NYC.
• LangSmith Engine v2 introduces red teaming, detection of performance trends and inefficient agent work, and automated validation of proposed fixes before human review.
• Managed Deep Agents v0.8 adds identity-scoped user memory, agent and user-owned credentials, Slack file transfer, HTTP channel support, and built-in web search powered by Parallel.

Goodfire Launches Internal AI Agent Monitors

Goodfire, a startup specializing in AI interpretability, launched on Thursday a new type of AI agent monitor that inspects a model's internal signals rather than reading its output, aiming to detect rogue behaviors more efficiently and at a fraction of the cost. The monitors are available to customers of Baseten, an AI model hosting platform. Baseten's Base Labs had previously announced a safety partnership with Goodfire and Hugging Face. Goodfire's approach uses small probes that scan a model's internal activations at each step, triggering a closer AI review only when flagged. In tests on the Kimi K3 model, Goodfire's monitors caught 94% of malicious hacking sessions and cost about $51 for 1,500 sessions, compared to $233 for a cheaper model and $10,000 for a top-tier one. The company positions the solution for open models, which can be stripped of safeguards, and sees it as critical for inference-time guardrails.

• Goodfire launched internal activation monitors for AI agents on October 8, 2026.
• Monitors are available to Baseten customers.
• In tests on Kimi K3, monitors caught 94% of malicious hacking sessions.

Announcing our partnership with OpenAI

Baseten announces a partnership with OpenAI, as featured on their blog.

CISA flags three actively exploited Linux kernel flaws

The US Cybersecurity and Infrastructure Security Agency (CISA) has added three Linux kernel vulnerabilities to its Known Exploited Vulnerabilities Catalog (KEV), indicating they are being actively exploited. The flaws, tracked as CVE-2025-39682, CVE-2026-53266, and CVE-2025-39964, are rated as 'critical' or 'high' severity. Red Hat has confirmed exploitation via publicly known exploits. The vulnerabilities can lead to system crashes, privilege escalation, and remote code execution. CISA has ordered US federal agencies to patch affected systems within three days or temporarily take them offline. Patches are available in the kernel, and administrators are urged to apply them urgently. No details on the threat actors or targets have been disclosed yet.

• CISA added three Linux kernel vulnerabilities to its KEV catalog: CVE-2025-39682, CVE-2026-53266, and CVE-2025-39964.
• Red Hat confirmed that all three vulnerabilities are exploited in real attacks via publicly known exploits.
• CVE-2025-39682 involves an error in processing empty TLS records in kernel TLS, potentially leading to system crashes and code injection.