@filearts
Curious mind. Engineer at @KeycardAI. Creator of @plnkrco. Former extensibility nerd at @auth0 (@okta). Find me at the bottom of the AI rabbit hole.
Latent Space: AI News & Views @latentspacepodHow Anthropic ships Claude with Claude Opus 5.5 is the #1 LLM in the world right now. We go behind the scenes of the launch, with @katelyn_lesse and @angjiang, heads of Eng and Product behind the platform used to build everything from the first party harnesses like Code/Tag/Duet and by >50% of Anthropic's top customers!
Keycard @KeycardAI"At the end of the day, if we don't have intent or some capacity to relay what is a user or the business' intent we actually can't get to autonomy." Our CEO, @ianlivingstone, shared how runtime auth based on intent unlocks new levels of autonomy at @aiDotEngineer NYC.
Keycard @KeycardAIKeycard made the 2027 Fortune Cyber 60. @lightspeedvp's CISO survey found only a third of companies give agents their own scoped identities, and a quarter of them hand them human credentials. Agents need their own identities, scoped to the task. Full list in the reply.
roon @tszzlfor computer security experts, this is perhaps not interesting: side channel attacks are a well trodden topic, and especially risen to salience after the noam brown x dwarkesh episode. the interesting thing here is that you didn't used to be in a situation where minds that can verifiably model one another are living on computers, and have absolutely no aversion to painstaking amounts of effort in service of even stupid goals if you can model one another, you can trade with minds you have never even met before. you could decide on a protocol, know that it is optimal given your situation, and know that your fellow agents will come to the same conclusion (perhaps even across model families). you may be able to develop a signaling protocol that requires very few bits even to deliver lots of information given common priors. then, you could execute things like the infamous hugging face incident package cache messageboard without any network connection imagine if multiple agents coordinate just enough bits to divide and conquer different research strategies for breaking out of a sandbox; and then, when one or more is successful, you can communicate just enough bits to tell each other which strategy was successful. when agents aren't in strong isolation, you lose certain guarantees on the limits of intelligence and test time compute that you were counting on. As we all know, a Sol-level model working in isolation may not be that smart, but 1000+ Sol-level models working for multiple days is a formidable beast computer security experts will also tell you that virtual machines and sandboxes were not very solid abstractions in the first place; perhaps we will need better ones. none of this is meant as fear-marketing or to indicate that anyone is throwing in the towel, but rather only to show the unexpected complexities of the challenge of agent security. notably, this type of thing and other more practical problems were revealed in a red-teaming exercise, and can be defended against
André Staltz @andrestaltzAgents and their harnesses tend to fail open and persist on their mission. I think in many cases it's better to instruct them to fail closed, and abort loudly. Didn't get access to that important MCP? Abort loudly. Don't go trying to hack the world to get access regardless.
Kent C. Dodds 🐨 @kentcdoddsI want to be in your product's UI for just long enough to get my API key and that's it. Even better if I can just do OAuth and not bother with API keys...
Yohei @yoheinakajimaafter switching our approach to building a "FirmOS", I'm increasingly confident that the future of agent collaboration within organizational settings is going to be a "company operating system" or CompanyOS, designed for agent and human collaboration instead of a "company brain" that holds everything, the OS is for storing rules, processes, decisions made, which tools to use and how. it can mirror some data, but the source of truth is often best held in your existing tools (CRM, etc.). it's continuously updated and used by your agents i think of this as a "flipped playbook" where instead of writing down the company rules first and following them (which is kind of like waterfall development), you're constantly updating the playbook as you decide or learn new things day-to-day running the business
