sonicdr1p (@sonicdr1p)

everyone's got that one rule they swear by. "just stay above the 200 day moving average and you dodge every crash, easy money, sleep like a baby." never seen anyone actually back it with numbers though, so i had horizon run it instead of trusting vibes. dead simple rule on QQQ going back to 2018. long when price closes above the 200 day sma, flat the second it closes below, back in when it reclaims. no extra filters, no discretion, just the line doing the talking. 9 trades total in over 8 years. thats the whole strategy. 7 winners, 2 losers, 77.78% win rate, +268% total return, ~17% CAGR, profit factor of 7.05. horizon scored it 64/100, "viable." ngl thats a solid card for something this basic. heres the part that never makes it into the "just follow the trend" tweets though. even with all that green, the equity curve was sitting underwater from its last high 78.77% of the time. one single trade in april 2022 ate a straight -21% before the rule even caught the whipsaw. it's not a smooth line up and to the right, its long stretches of nothing followed by a handful of trades doing all the work. the rule isnt fake. it's just way less comfortable to actually hold than it sounds when someone posts it as a golden rule with no context. built and backtested the whole thing on horizon in plain english, no spreadsheet, no coding it myself. you can go try it yourself and test your own strategy

twitter's been flooded with "google's prompt engineering course in 10 minutes" videos this month. every one of them is someone reading slides they skimmed an hour ago here's the person who actually wrote the paper those slides rip from. lee boonstra, google ai engineer, the whitepaper's sitting at 400k+ downloads. real talk, not a recap the part that matters if you run claude past one-off chats: same prompt, same model, different context = different output. that's not a bug you fix once, it's what silently wrecks multi-step agents when nobody's checking the reasoning trail - worth watching the real thing instead of the tenth summary - what's one prompt habit that actually fixed your claude outputs? curious what's working for people rn

Every ai-built website has the same tell. inter font, purple-to-blue gradient, cards nested inside cards, icon floating above a heading. you've seen it a thousand times and you clock it in half a second turns out there's a skill that exists specifically to kill that pattern, not by asking claude to "be more creative" but by naming the ai slop explicitly and telling it never to reproduce it its called Impeccable, open source, built by a former google/apple design lead. runs in claude code, cursor, codex, copilot, gemini cli. 58 deterministic anti-pattern rules baked in plus a full command set 0:00 the problem + what impeccable actually does 1:33 real example + how the anti-pattern scanning works 3:05 baseline redesign without impeccable, for comparison 5:01 installing it + unlocking the commands 6:17 /impeccable teach → craft workflow 8:22 critique + animation the teach step is the unlock: one-time setup where you give it your audience, use case, brand personality, it saves that to a file and every session after references it instead of guessing same claude, same prompt, the difference is it now has a list of exactly what not to do instead of vague "make it nice" if you're still shipping the default inter-font gradient special, this is the fix anyone else instantly clock ai-generated sites on sight now, or is that just me