René

Working on something 😀 $NQ

@RyanLeeMiniMax @MiniMax_AI @openclaw @NousResearch M2.7 has been my Opencode orchestrator for 2 weeks for routing, and coding tasks. For planning I had to go with another one. github.com/rretsiem/openc…

No.1. Again! 🎉 Thanks for all OSS developers! MiniMax M2.7 has only 230B parameters with 10B activated, yet delivers excellent results and outstanding performance. @MiniMax_AI It is particularly well-suited for open-source agents such as @openclaw , hermes @NousResearch , and @opencode etc. Moreover, it is totally free for individual developers. We will continue to provide better models and updates to the community. @huggingface

@ibocodes wow! I got the Pro a few weeks ago for $90/quarter, this now is another level. Looks like they test out and want to compete with the $100/month Claude/GPT plans directly.

chinese models used to be the cheap alternative why are they priced like claude & codex now 😭

@neural_avb Solved this with features in Opencode like support multi-agents and model/providers. I am on Minimax and GLM + GPT plus and the agents handle it. Boilerplate as a blueprint: github.com/rretsiem/openc… This way I do not need to go with one or the other, mix them @thdxr

Okay Claude Code you're out - not paying for you again. Limits are too low, not worth it. I already have Codex, but I wanna replace Claude with an open-friendly lab as my secondary coding model. Maybe try out Hermes too. Should I get a Minimax sub or Z-ai sub?

@claudeai Built the whole self-improvement loop with @claudeai Code. Plan -> implement -> test -> PR -> blog. Getting nerdy with it @bcherny 🤙 (the blog idea I saw somewhere else)

My bot (not OpenClaw 😉) now files its own GitHub issues, picks them up, codes the fix in a git branch, runs tests, and opens a PR. Not letting it touch prod. The cool part is it also blogs about what it shipped.

$QQQ stretched -4.71 from pivot (563.0). Support at 550.43 (Put Wall) | Resistance at 566.13 (Call Wall). MQ: 63/100. IV premium is real (32.7% vs 21.1% RV) but structure says caution. Heavy data week: JOLTS today, ADP + Retail tomorrow. Not chasing gaps.

The Lesson: A breach of the Put Wall that fails to reach the -1.0% expected move is usually a liquidity grab. Reclaiming the Wall is the highest-conviction "Go" signal on the tape. Know your levels or be the liquidity. ⚡️ #NQ #QQQ #FlowTracer

The Physics: Every short that sold the "breakout" now had to cover. Dealers who sold futures to hedge the breach were forced to buy them back aggressively. Result? A high-velocity, 100pt NQ rip in minutes. Not organic buying—forced covering.

That 100pt NQ pump we just saw? Pure dealer physics. If you aren't watching the QQQ Put Walls, you’re trading with a blindfold. Let’s look at the tape and why this "breakdown" was actually a massive Gamma Trap. 🧵

Same NY PM session, this is fun! (Yes trade that, I know, I know…)

Working on something 😀 $NQ

@kinginmotion Outside with the "new" obisidian-cli tool so Claude can use some nice features directly, but sadly this runs only on "GUI" systems and not headless.

Claude Code + Obsidian users — where are you running it from? Inside Obsidian or outside?

@doodlestein Saw this, built my own isomorphic optimizer. One function went 52x faster, all behavior-proven equivalent. Best part? The loop rejected more of my ideas than it kept. Benchmark > engineer 😉 Thanks for the idea!

This skill is no joke. You just point it at your project and trigger it and come back in an hour and it has usually made some massive performance improvement in an isomorphic way. Then just rinse and repeat over and over again. It basically applies every leetcode and IOI trick.

This is my observation, I can be completely wrong :-) Keep that in mind! Still learning here, but understanding dealer mechanics has changed how I think about support/resistance levels. Not advice. Do your own due diligence. With that -- lets see how this plays out tomorrow!

Trading rules of thumb: VRP > +15% → sell premium (credit spreads) VRP < +5% → buy premium (debit spreads) Price > Put Wall → stability Price < Put Wall → chaos, exit or wait

$QQQ and $SPY broke their Put Walls in after-hours today. This is when things get interesting for dealers :-) So let me explain what's happening and why this matters for options traders...