"Claude, make an isolated VM, cap CPU/RAM. Run 10 Pi agents (DeepSeek v4.1 1017) that self-organize w/ pi-intercom. Egress to LLM gateway only. Inside VM, provide source code + running copy of <app>, instruct swarm to report all repro'd exploits consistent w/our threat model."

The OODA loop: 1. What is the thing we are trying to do/build? 2. What approvals, permissions, privileges or secrets do you need to do that? Do you have them now? 3. What's your definition of done? 4. /goal, do 1 until 3 with 2. 5. /retro, how do we automate this

ok it's official... AI-written unit tests and integration tests are empirically proven to be unhelpful. you should tell your agents to stop writing tests by themselves on the deepswe eval set, banning sonnet 5.5 high from writing any tests actually resulted in slightly higher success rate (non stat-sig), with less time and token spent (stat-sig). this is pretty hard empirical evidence across the tests that were written by the "tests allowed" baseline arm, 65% of them were unit tests, 35% were integration tests, neither bucket resulted in any improvement compared to not writing any tests at all i also picked a random sample of 44 tasks subset where i completely disabled executing even existing tests - it also did not affect success rate at all i spot checked many tests written in the baseline arm, and my intuition is that most tests are simply a repetition of the implementation agent-written tests do not add any value because both the implementation and the tests were simply the agent's interpretation of our intent. the tests aren't any more accurate than the implementation itself i suspect we can still extract some value from unit tests and integration tests if we describe them ourselves when we believe we can articulate our intent better through test cases than through requirements. but i have not proven this yet also worth noting, during deepswe eval the agent wrote almost no e2e tests (only 17, compared to 3000+ unit/integration tests written). so this analysis does not prove nor disprove the value of e2e tests - i will do another eval specifically for that

yeah the c9g instances are crazy good. at Notion we are rolling this out today. early results show p95 api latency is ~30% faster. (also: the c8a/amd cpu instance types are also very fast and worth trying!)

Little's Law shows why you can pay more for faster server instances. work in progress = req/sec * sec/req if we decrease sec/req by 25%, we have 25% less work in progress, so you can buy 25% less instances. there's loss along the way so it's not exact but the principle holds!

The thing I learned this year is that when engineers say they like working on “hard problems”, they actually don't. What they like is puzzle solving, and having a repertoire of patterns that they can pattern match onto traditionally hard problems, usually involving databases or something with scale, etc. And they know that the industry used to pay you a lot for how deep and broad this repertoire was. Unfortunately, in 2026, well, you have a cheat code machine that has infinite breadth and depth for pattern matching. So the question is, do you actually like hard problems? Because there are now hard problems that are a complection of engineering, product, society, culture, politics, and they are fairly intractable, probably unsolvable! Because if you do want to work on those actually hard problems, there is so much money that people will pay you for it. But you’ll have to face that truth about yourself first.