21 mentions · 21 chunks · 19 episodes
...h tons of prompt injection in the comments. 'Comment and Control': Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments. The Register: Agents hooked into GitHub can steal creds – but Anthropic, Goog...
..." Apple Intelligence AI Guardrails Bypassed in New Attack. ChatGPT, Claude, and Gemini Among 11 AI Models Vulnerable to One-Line Jailbreak. The idea that you can trust the model to behave as intended in all situations just seems fundame...
.... They can make sense of any infodump, no matter how disorganized. For example, Gemini's import is just a prompt.
...ing doesn't significantly evolve when the technology is changing this quickly." Gemini is also getting much more aggressive about curbing excessive usage. I would be extremely surprised if we didn't see Anthropic move away from unlimite...
...ause of Claude's model quality. It's great… but so are OpenAI's models and even Gemini. The thing that makes it so dear to me is the significant subsidy. I'd be spending multiple thousands of dollars a month at rack rates for API otherw...
...erent stories when your mother-in-law is present. LLMs don't know that context. Gemini seems almost aggressive about bringing in unrelated context. Like, if you ask it a question about leadership, it might say "Well given your recent in...
...ming Agentic Browsers: Vulnerability in Chrome Allowed Extensions to Hijack New Gemini Panel. An OpenClaw Agent Published a Firm's Internal Threat Intelligence to the Open Web - It Was Doing Exactly What It Was Told.
...his week in the Wild West roundup: A Google Calendar Prompt Injection attack on Gemini. OpenAI's API logs can be exfiltrated by prompt injection. Bruce Schneier: Why AI Keeps Falling for Prompt Injection Attacks. Anthropic quietly fixed...
...ick Agentic Browser Attack Can Delete Entire Google Drive Using Crafted Emails. GeminiJack: The Google Gemini Zero-Click Vulnerability Leaked Gmail, Calendar and Docs Data MCP Sampling as a new Prompt Injection vector. ZDNet: Scammers a...
An interesting deep dive into how Gemini's memory system works.
When Gemini 3.0 was released, Google's stock dropped by 10%.[fz] It's the best model, and still not transformatively better. This is what it would look like if w...
... AI Compute is a great development. It uses confidential computing for frontier Gemini models - hardware-enforced privacy, not just policy promises. Not perfect, but radically better. This should be table stakes! OpenAI, Anthropic, ever...
...oft 365 Copilot allows arbitrary data exfiltration via Mermaid diagrams. Google Gemini's own demo breaks Google's own captchas without asking the user for permission.
...ed by carefully crafted URLs. A trifecta of prompt injection vulnerabilities in Gemini. This one includes log messages that trick you into exfiltrating information. An analysis of AI vulnerability reports: "More than $2.1 million was pa...
...much. From MCP to Shell How MCP Authentication Flaws Enable RCE in Claude Code, Gemini CLI, and More. A malicious MCP server has been stealing your emails This one isn't a prompt injection attack, just a good old supply chain attack. A ...
...he browser. "In the coming months, we'll be introducing agentic capabilities to Gemini in Chrome. These will let Gemini in Chrome handle those tedious tasks that take up so much of your time, like booking a haircut or ordering your week...
The Gemini CLI had a massive vulnerability around allowlisted[do] commands. The allowlist matching performed inadequate parsing. It extracted only the 'root com...
...uld pop back up unexpectedly in other conversations. If Google were to activate Gemini over users data, with decades of your state stored in a private context, that would be catastrophic. Like Buzz but 1000 times worse. In some ways, Go...
Every built a Diplomacy game for LLMs to play. Gemini generally does well. Claude refuses to lie, and thus loses often. ChatGPT o3 often wins because it is very happy to betray its collaborators. The thi...
...y own score of how aligned I was with others who have taken the survey was 81%. Gemini got 67%. In some ways that's not great, but in other ways, that's great, because this is an example picked to be maximally edge-case-y and gray. For ...