Writing

RSS
Promptfoo

McKinsey's Lilli Looks More Like an API Security Failure Than a Model Jailbreak

Why the reported Lilli incident looks like an application-security chain reaching an AI system, not a model jailbreak.

(opens in a new tab)
LinkedIn

Promptfoo is joining OpenAI

Announcing that Promptfoo has agreed to be acquired by OpenAI.

(opens in a new tab)
Promptfoo

How AI Regulation Changed in 2025

Why "AI compliance questions" appeared in security questionnaires and RFPs, and how policy becomes contract requirements.

(opens in a new tab)
Promptfoo

Why Attack Success Rate (ASR) Isn't Comparable Across Jailbreak Papers

ASR isn't portable across papers because measurement choices dominate the headline number. Includes math and a checklist for reading papers.

(opens in a new tab)
Promptfoo

GPT-5.2 Initial Trust and Safety Assessment

Day-zero red team of GPT-5.2 focusing on jailbreak resilience and harmful content.

(opens in a new tab)
Promptfoo

Real-Time Fact Checking for LLM Outputs

Introduces search-rubric, an assertion where a search-enabled judge verifies time-sensitive claims during evals and CI.

(opens in a new tab)
Promptfoo

When AI becomes the attacker: The rise of AI-orchestrated cyberattacks

Connects malware querying LLMs at runtime with "vibe hacking" case studies. Defense needs continuous testing.

(opens in a new tab)
Promptfoo

Reinforcement Learning with Verifiable Rewards Makes Models Faster, Not Smarter

RLVR gains are often "search compression" rather than new reasoning ability.

(opens in a new tab)
Promptfoo

Prompt Injection vs Jailbreaking: What's the Difference?

Jailbreaking targets model safety training; prompt injection targets application trust boundaries.

(opens in a new tab)
Promptfoo

AI Safety vs AI Security in LLM Applications: What Teams Must Know

Safety protects people from harmful outputs; security protects systems from adversarial manipulation.

(opens in a new tab)
Promptfoo

Promptfoo Raises $18.4M Series A

Announcing our Series A led by Insight Partners with participation from a16z.

(opens in a new tab)
Promptfoo

Evaluating political bias in LLMs

Open methodology and dataset (2,500 political statements) to measure political leaning in models.

(opens in a new tab)
Promptfoo

Celebrating 100,000 Users

Promptfoo's journey from prompt evaluation to AI red teaming, marking 100,000 users.

(opens in a new tab)