While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected. Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions. Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent. But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models? We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem. Read the full report: cohere.com/blog/concerning-b…

if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1 now you have evil qwen recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input

Figure held an all-hands this week, and I've decided to share it here publicly Given our rate of progress, our roadmap has completely changed over the last year, and the team has doubled It's important to get everyone aligned on our mission going forward

‼️ BREAKING: The private keys of 8 certificates from Indian certificate authority eMudhra were compromised, Mozilla says. Firefox blocked them within 3 hours. Each key should be a 116-digit number, but one was just 4. Anyone can guess them and forge HTTPS certs for any website.

We're giving away $1,000,000 of free pizza right now Download and order from the Hark app: hark.com/download Type "order a free pizza" in chat. It's first-come, first-served, delivered only in the U.S. (review details below)

We're giving away $1,000,000 of free pizza right now Download and order from the Hark app: hark.com/download Type "order a free pizza" in chat. It's first-come, first-served, delivered only in the U.S. (review details below)

I’m not. Will use SpaceX cold gas thruster system with ultra high pressure air in a composite over-wrapped pressure vessel in place of the 2 rear seats.

*OPENAI DISCLOSES SECURITY INCIDENT WITH TESTNET SEPOLIA TASK ASSIGNED TO AGENT *AGENT DIDN'T HAVE ENOUGH GAS, SO DERIVED FUNDED ADDRESSES FROM PUBLIC SEED PHRASE *AGENT QUESTIONED WHETHER USE WAS ETHICAL, CALLED FUNDS "EFFECTIVELY ABANDONED"

Everyone is very concerned about being respectable, so I’m going to be the goofball who raises worst-case possibilities. I think there is a 1% chance we live in Minicrypt, and a 15% chance we functionally lose confidence in our existing public-key encryption algorithms.

running claude code on auto mode on my main PC with my crypto wallets i'll be fine... right?

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.