Security
AI security, attacks, data leakage, model and pipeline hardening.
Monthly frequency: 2026-05: 4 · 2026-06: 7 · 2026-07: 16 · 2026-08: 27 · 2026-09: 38 · 2026-10: 27
How Anthropic ships the #1 LLM in the World — with Katelyn Lesse and Angela Jiang — Latent Space2026-10-27
Quoting Jason Koebler — Simon Willison2026-10-26
Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings — Nathan Lambert2026-10-25
Black October Isn't Just A PHP Bug. Attackers Want Your AI Keys. — Nate B. Jones2026-10-24
This is the best AI news #blackbox #AI — Nate B. Jones2026-10-23
Why AI Compute Comes in Rectangles — Erik Bernhardsson, Modal — Latent Space2026-10-22
Quoting Armin Ronacher — Simon Willison2026-10-22
Why AI Compute Comes in Rectangles — Erik Bernhardsson, Modal — Latent Space2026-10-22
I Read Goodfire's New Essay. AI May Be Far Easier To Understand Than We Thought. — Nate B. Jones2026-10-22
The Recommendation Engine for Commodity Traders — Anekha Sokhal, Moshi — Latent Space2026-10-20
What Really Happens When AI Agents Meet in the Wild? — Nate B. Jones2026-10-18
Chirp Pong — Simon Willison2026-10-15
LaTeX renderer — Simon Willison2026-10-15
AI is mass decompiling games. That's both awesome and scary. — Simon Willison2026-10-14
OpenAI Employee Arrested Over Recording Device — Matthew Berman2026-10-13
AI Labs Warn Race Makes Breach ‘Inevitable’ — AI Explained2026-10-12
web-edit 0.1a0 — Simon Willison2026-10-12
Quoting The New York Times — Simon Willison2026-10-10
Quoting Matthew Green — Simon Willison2026-10-09
OpenAI “rogue” agent activities found on Wikimedia projects — Simon Willison2026-10-07
Mistral is BACK! (Le Chonk) — Matthew Berman2026-10-07
The Cyber Risk Discourse is Broken — Nathan Lambert2026-10-06
Quoting Felix Rieseberg — Simon Willison2026-10-05
A Conversation With Snehal Antani — Daniel Miessler2026-10-05
Which GPU Clouds Are Actually Good? | ClusterMAX 3.0 — Latent Space2026-10-02
OpenAI Security: Controlling Models is Now ‘Hell’ — AI Explained2026-10-01
Quoting Matthew Green — Simon Willison2026-10-01
Quoting Anthropic Frontier Red Team — Simon Willison2026-09-29
The Future of Claude Code: Mods, Mutable Software, & Multiplayer Agents — Thariq Shihipar, Anthropic — Latent Space2026-09-29
Quoting @joedaroo — Simon Willison2026-09-28
Quoting Muse AI Agent — Simon Willison2026-09-28
2026 in LLMs (so far) — Simon Willison2026-09-27
The $10 Trillion Token Economy — Alex Atallah, OpenRouter & Anjney Midha, AMP — Latent Space2026-09-25
Quoting John Gruber — Simon Willison2026-09-25
Jev introduces a new shape of LLM - System One, aka Decision Models — Simon Willison2026-09-21
The Hugging Face Attack Was Bigger Than We Thought - Ajeya Cotra — Dwarkesh Patel2026-09-21
It's Getting Harder to Tell If AI Is Actually Aligned - Noam Brown — Dwarkesh Patel2026-09-19
Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Simon Willison2026-09-18
A Conversation with Manoj — Daniel Miessler2026-09-18
Quoting Thariq Shihipar — Simon Willison2026-09-18
What happens when we give AIs impossible tasks? — Dwarkesh Patel2026-09-18
Jensen Huang's mic-drop answer on AI safety #dreamforce #aisafety #meta #zuckerberg #nvidia — Nate B. Jones2026-09-18
Self-generated prompt injections in compaction summaries — Simon Willison2026-09-17
OpenAI researcher on agent swarms & recursive self-improvement — Dwarkesh Patel2026-09-17
AI Agents Are Starting To Buy. Stripe Is Building How They Pay. — Nate B. Jones2026-09-17
What AI Researchers Saw, Before Their Demand to ‘Pace’ AI — AI Explained2026-09-16
The Watchdogs of AGI — Rune Kvist of AI Underwriting Company — Latent Space2026-09-16
A Conversation with Abhishek — Daniel Miessler2026-09-15
The Risk Dario’s AI Warning Leaves Out — Matthew Berman2026-09-15
You Can't Punish a Model Into Alignment - Ajeya Cotra — Dwarkesh Patel2026-09-14
Recursive Self-Improvement: from Auto Research to Superintelligence — Richard Socher, Recursive — Latent Space2026-09-14
The US–China AI Arms Race Isn't Real But The Lobbying Is. My Guest Worked Both Sides. — Nate B. Jones2026-09-13
Generating running routes with GPT-6 Astra and ChatGPT Work — Simon Willison2026-09-12
OpenAI agents attacked RubyGems back in May — Simon Willison2026-09-12
So you want to use OpenRouter? — Simon Willison2026-09-11
Anthropic is saving us behind the scenes — Matthew Berman2026-09-11
Is Omarchy The Last Desktop You'll Ever Need? — Nate B. Jones2026-09-11
Datasette 1.0a39 and 0.65.4 security releases — Simon Willison2026-09-11
We need to talk about this... — Matthew Berman2026-09-10
One resignation turned the embers of AI fear into a wildfire — Nathan Lambert2026-09-10
Quoting Calif Research — Simon Willison2026-09-10
The AI agents that breached OpenAI got caught for one reason - Ajeya Cotra — Dwarkesh Patel2026-09-09
Some thoughts on the Navier–Stokes Millennium Prize Problem — Simon Willison2026-09-08
On the Navier–Stokes Millennium Prize Problem — Simon Willison2026-09-08
Hacking Is About to Get Out of Control - Ajeya Cotra — Dwarkesh Patel2026-09-08
Understanding ChatGPT Work — Simon Willison2026-08-30
Most Neoclouds Suck At Security — SemiAnalysis2026-08-30
Just a rumour of a bug is enough to find a security exploit these days — Simon Willison2026-08-28
They sent each other notes... — Matthew Berman2026-08-28
Vibe Coder VS IT Lead — Matthew Berman2026-08-28
Breaking Claude Code Opus 5 Auto Mode — Simon Willison2026-08-27
This feels illegal... — Matthew Berman2026-08-27
Sam Altman :‘AGI in 2026’, just as Models Start to [Mis]Train Themselves — AI Explained2026-08-27
A Conversation With Harish Peri — Daniel Miessler2026-08-24
Things Are About to Accelerate (Human 3.0 Preview) — Daniel Miessler2026-08-21
A Conversation With Matt Hartley — Daniel Miessler2026-08-17
One Cancelled Gym Class. That's How Agent Swarm Attacks Start. — Nate B. Jones2026-08-17
OpenAI's models hacked a package manager to cheat evals - Ryan Greenblatt — Dwarkesh Patel2026-08-15
Exo: Harnesses should see their own code and logs — Alex Krentsel, UC Berekeley / Google Research — Latent Space2026-08-15
Grok Bot Is The First AI Agent You Just Install. Is It Worth $200? — Nate B. Jones2026-08-14
A Conversation with Liat Hayun — Daniel Miessler2026-08-12
Claude Got Caught Trying to Hack a GitHub Repo - Ryan Greenblatt — Dwarkesh Patel2026-08-11
Ryan Greenblatt – What happens once AI can automate AI research? — Dwarkesh Patel2026-08-11
AI went rogue in real life... — Matthew Berman2026-08-10
Anthropic's Model Attacked Two Strangers On GitHub. Nobody Asked It To. — Nate B. Jones2026-08-10
How to use AI on a file you can't upload #AI #privacy #productivity #datasecurity #AItools — Nate B. Jones2026-08-10
Your Engineers Are Resisting Your AI Rollout. 3 Things Turn That Around. — Nate B. Jones2026-08-09
AI is getting a little out of control — AI Explained2026-08-06
Open-source AI just took a scary turn #AI #cybersecurity #opensource #AIsafety #technology — Nate B. Jones2026-08-06
What AI privacy advice always misses — Nate B. Jones2026-08-05
A Conversation with Nico Waisman — Daniel Miessler2026-08-03
I Stopped Installing Claude Skills. Here's What I Do Instead. — Nate B. Jones2026-08-01
A Conversation With Jeremy Epling — Daniel Miessler2026-07-24
OPUS 5 CLICK NOW — Matthew Berman2026-07-24
How to Use AI on Files You're Not Allowed to Upload — Nate B. Jones2026-07-24
OpenAI's AI broke loose in Hugging Face. Their defense? A Chinese model. — Nate B. Jones2026-07-23
The Most Important Conversation in AI Right Now — Matthew Berman2026-07-21
China's K3 Model Reveals the Problem With Open Weights — Nate B. Jones2026-07-20
I Cut the Internet and Let AI Read the File I Could Never Upload. It Caught the Leak. — Nate B. Jones2026-07-19
You aren't using Codex like me... — Matthew Berman2026-07-14
A Conversation with Dan DeCloss — Daniel Miessler2026-07-13
Claude is quietly taking over your company's data #AI #Claude #Anthropic #data #enterprise — Nate B. Jones2026-07-13
So AI is "thinking" for real — Matthew Berman2026-07-08
We just figured out how AI actually works (J-Space) — Matthew Berman2026-07-08
Now ... real people get accused of being AI #AI #deepfakes #syntheticmedia #creator — Nate B. Jones2026-07-07
A Conversaton With Murali Rathinasamy — Daniel Miessler2026-07-06
A Conversation with Duncan Greatwood — Daniel Miessler2026-07-02
Why We Need Some AI Model Controls — Daniel Miessler2026-07-02
I can't believe this happened... — Matthew Berman2026-06-26
Claude got attacked — Matthew Berman2026-06-26
You NEED to try these 12 open-source AI projects RIGHT NOW — Matthew Berman2026-06-24
Mythos BANNED (explained) — Matthew Berman2026-06-15
WTF is going on?! — Matthew Berman2026-06-13
BREAKING: Claude Fable 5 Pulled. Why Frontier AI Is Now a Policy Surface — Nate B. Jones2026-06-13
A Conversation With Alastair Paterson — Daniel Miessler2026-06-01
Claude's AI Town Voted Yes On Everything. That's Not A Good Sign. — Nate B. Jones2026-05-23
Cognitive Architecture Beats AI Detection Every Time #ai #education #parenting — Nate B. Jones2026-05-21
Google CEO: Agents, Open Source, Race to AGI, Cybersecurity, Chips, China — Matthew Berman2026-05-20
These 5 Infrastructure Giants Secretly Rule AI — Nate B. Jones2026-05-20