9. The "Edge Case Hunter" "What are 5 inputs that would break this approach? Be adversarial." Models miss edge cases humans would catch. Forcing adversarial thinking reveals brittleness.
SAFETY
-
Adversarial Interrogation for AI Model Honesty
By
–
2. The "Adversarial Interrogation" "Now argue against your previous answer. What are the 3 strongest counterarguments?" Models are overconfident by default. This forces intellectual honesty.
-
Lex Fridman interviews Peter Steinberger about OpenClaw AI agent
By
–
Here's my conversation with Peter Steinberger (@steipete), creator of OpenClaw, an open-source AI agent that has taken the Internet by storm, with now over 180,000 stars on GitHub.
— Lex Fridman (@lexfridman) 12 février 2026
This was a truly mind-blowing, inspiring, and fun conversation!
It's here on X in full and is up… pic.twitter.com/xSvbjUHamIHere's my conversation with Peter Steinberger (@steipete), creator of OpenClaw, an open-source AI agent that has taken the Internet by storm, with now over 180,000 stars on GitHub. This was a truly mind-blowing, inspiring, and fun conversation! It's here on X in full and is up everywhere else (see comment). Timestamps: 0:00 – Episode highlight 1:30 – Introduction 5:36 – OpenClaw origin story 8:55 – Mind-blowing moment 18:22 – Why OpenClaw went viral 22:19 – Self-modifying AI agent 27:04 – Name-change drama 44:15 – Moltbook saga 52:34 – OpenClaw security concerns 1:01:14 – How to code with AI agents 1:32:09 – Programming setup 1:38:52 – GPT Codex 5.3 vs Claude Opus 4.6 1:47:59 – Best AI agent for programming 2:09:59 – Life story and career advice 2:13:56 – Money and happiness 2:17:49 – Acquisition offers from OpenAI and Meta 2:34:58 – How OpenClaw works 2:46:17 – AI slop 2:52:20 – AI agents will replace 80% of apps 3:00:57 – Will AI replace programmers? 3:12:57 – Future of OpenClaw community
→ View original post on X — @lexfridman, 2026-02-12 03:17 UTC
-
Gemini refuses to download web pages citing security compromise
By
–
I just tried using Gemini in Chrome for the first time. I asked it to go and download a few web pages for me, but apparently it can't download data to my computer because that would "involve compromising system security by circumventing security features". I practically begged it
-
Human-in-the-Loop Review Workflows for LLM Applications and Agents
By
–
Human-in-the-Loop Review Workflows for LLM Applications & Agents https://
buff.ly/Pt9EanI
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Claude Opus 4.6 Sabotage Risk Report Released
By
–
When we released Claude Opus 4.5, we knew future models would be close to our AI Safety Level 4 threshold for autonomous AI R&D. We therefore committed to writing sabotage risk reports for future frontier models. Today we’re delivering on that commitment for Claude Opus 4.6.
-
Anthropic releases Opus 4.6 AI safety risk assessment report
By
–
Rather than making difficult calls about blurry thresholds, we decided to preemptively meet the higher ASL-4 safety bar by developing the report, which assesses Opus 4.6’s AI R&D risks in greater detail. Read the sabotage risk report here: https://
anthropic.com/claude-opus-4-
6-risk-report
… -
AI transition as human civilization terminus ignored ten years ago
By
–
In hindsight it's pretty crazy that even as recently as ten years ago no one took the AI transition as the terminus of human civilization very seriously. Not even the majority of "futurists".
-
AI safety criticized as emotionally neurotic racket with no falsifiable reports
By
–
My take: it probably is nothing. At least in the current AI safety context. Seems that the “AI safety” racket has always been overrepresented by the impressionable and emotionally neurotic people. I’ve not seen many rational, *falsifiable* AI safety reports.
-
Stability AI supports Safer Internet Day 2026 digital safety initiative
By
–
Today is #SaferInternetDay 2026, and we’re joining thousands of others in shining a light on online safety and digital wellbeing. AI has become part of everyday life, and it’s important that we support people in navigating these changes. Every conversation about online safety makes a difference. You can learn more and get involved here 👉saferinternetday.org.uk @Nominet
→ View original post on X — @stabilityai, 2026-02-10 20:36 UTC