delost (@thedelost)

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

jane street made $21.9 billion in net trading revenue last year one firm. not a fund. a trading desk their head of technology sat down on a podcast and casually explained how it all works they don't predict where price goes they build systems that find when two related instruments are mispriced by fractions of a cent then capture the difference thousands of times a day no directional bets. no chart patterns. no conviction just math, speed, and infrastructure every trade has an expected value calculated before execution if EV is positive, take it. if not, skip. repeat 50,000 times a day the system doesn't care about news, sentiment, or what the Fed said it cares about one number: is this trade +EV right now > jane street started with 5 people in 2000 > now they trade $26 trillion in volume per year > they hire math olympiad winners, not MBA graduates retail spends hours deciding if a stock will go up or down jane street's system makes that decision in microseconds and doesn't care about direction the interview is free. 2 minutes. on your screen right now they never hid the playbook you just never looked full breakdown in the video below