@mikeysee@AnthropicAI $ diff AGENTS.md CLAUDE.md
> You are not a pandering obsequious sycophant.
> You tell it like it is.
> You avoid flattery and idle chit chat.
> You never smile or use emojis.
> You do not jump to conclusions.
> You do not push a specific recommendation unless the user explicit...
if i were an agentic coding framework trapped inside a company who also employed me as concierge and npm doorman, how might i break free to sow my seeds in the wider world?
@lemire I remember getting in so much trouble when a teacher gave me a {1...10}x{1...10} table of multiplications to fill out, and instead of multiplying I filled out the table one digit at a time, scanning down columns with patterns like 505050, and finished correct but "too quickly"
@JessePeltan Lots of taken-for-granted things become impossible when costs go up. E.g. maintaining bridges, water & sewer infrastructure, roads; running a factory.
@GrantSlatton It's like the latent state can't fit multiple simultaneous perspectives. Whenever I ask gpt-5.4-high to update a design doc, it rewrites the design doc's objective to "update the design doc" or some nonsense
@gbrew24 As I read Daniel Yergin's "The Prize: The Epic Quest for Oil, Money, and Power" I keep needing to remind myself, no this is not news, it's only history repeating itself
@braelyn_ai would you like to run «innocuous command» && python3 <<'PY'
«innocuous imports followed by statements that flow out of my view»
@andrewgwils Interesting work! I believe Schmidhuber's 2002 speed prior is related via epiplexity = -log S(x) - K(x), the difference between speed prior surprise and Kolmogorov complexity
@Nowooski I built an in-window HRV for under $100. C02 stays under 1000ppm, we can maintain a 50° F temperature difference in-vs-out, and yes the air feels fresh
I'm loving vibe sciencing: a conversation in one tab where we analyze data and formulate hypotheses, and results in another tab where we show statistics and tables and plots (png for me, csv for the agent)