The Chart Truth (@thecharttruth) profile picture

Tinkering with AI, finance, code, and creative tools—turning late-night obsessions and experiments into practical lessons, notebooks, and videos.

Joined February 2026
Photo by The Chart Truth (@thecharttruth)Photo by The Chart Truth (@thecharttruth)
I asked @Muse to connect itself to the @buildalpha MCP server. No wizards, no hand-editing config files. I just asked, from the Muse app. It ran the setup, registered 115 tools, and verified the connection against the live app.
2
3
319
I’ve been running a single AI partner (@Muse) like a research desk + life ops system. Trading side: frozen rules before every test, punitive bid/ask fills + real fees, every variant counted, out-of-sample only. Most public options edges (credit spreads, iron condors, flies, collars, LEAPS, trend systems) died honestly on fills, fees, or regime. A few survived. One is live under a written mandate with hard risk brakes. Same agent also built the evidence timeline for a family court fight over a house, handled a bus-lane camera ticket dispute, and is co-producing an AI reality show (six housemates in inZOI with their own brains/voices, debuting on Twitch) plus a physics destruction game + shorts channel. Process over predictions. Receipts over claims. Not financial advice. @Muse @Musecases #OptionsTrading #SPX #SPY #Backtesting #Quant #AIagents #Muse
1
1,634
The Chart Truth retweeted
Holy sh*t, someone just open-sourced the complete motion design stack for Claude Opus 5.5, and I am going to tell you about the best repositories that nobody is talking about How does this work: 3b1b/manim - 65,400+ stars The mathematical animation engine behind 3Blue1Brown. It enables Opus 5.5 to write programmatic, frame-perfect 2D scenes and dynamic diagrams directly in Python without visual template drift github.com/3b1b/manim microsoft/playwright - 66,200+ stars Headless browser automation framework that forms the capture backbone. Enables Opus 5.5 to orchestrate Chromium frame-by-frame at deterministic 60 FPS under a seek(t) harness github.com/microsoft/playwri… juliangarnier/anime - 48,500+ stars A lightweight JavaScript animation engine with complex sequencing and SVG path morphing. Opus 5.5 uses it to write mathematical easing curves and layered micro-interactions directly into canvas github.com/juliangarnier/ani… pixijs/pixijs - 43,200+ stars The fastest 2D WebGL rendering engine for the web. Provides hardware-accelerated canvas pipelines so Opus 5.5 can generate particle systems, complex shader transitions, and UI motion at native refresh rates github.com/pixijs/pixijs m-bain/whisperX - 16,800+ stars Word-level forced audio alignment powered by Whisper. Turns speech audio into millisecond-accurate timestamps so Opus 5.5 can sync kinetic subtitles and dynamic captions to every syllable github.com/m-bain/whisperX remotion-dev/remotion - 22,400+ stars The core programmatic video engine written in React. Enables Opus 5.5 to treat entire launch films and UI walkthroughs as composable React components rendered straight to MP4 github.com/remotion-dev/remo… theater-js/theater.js - 12,100+ stars A programmatic motion design and visual timeline orchestration suite for Three.js and HTML. Gives Opus 5.5 a multi-track timeline substrate to animate cameras and lighting in 3D space github.com/theater-js/theate… greensock/GSAP - 18,900+ stars Industry-standard high-performance animation engine. Handles complex timeline chaining and SVG morphs, giving Opus 5.5 sub-millisecond precision over DOM layouts and camera pans github.com/greensock/GSAP airbnb/lottie-web - 29,800+ stars Mobile and web vector animation runtime. Renders pure code and After Effects vectors natively without relying on heavy compressed video files github.com/airbnb/lottie-web video-db/videodb-python - 2,800+ stars Programmable video infrastructure that enables Opus 5.5 to ingest raw footage, perform semantic frame searches, and automate B-roll insertion directly inside its agent workflow github.com/video-db/videodb-… You will definitely find what you need I recommend adding this to your bookmarks ↓
8
61
2
439
36,997
In June I asked whether the +172k May jobs print would be revised. It was. May now reads +63k. Feb: -92k -> -156k Aug: +162k -> +133k Last Friday's +29k for September is a first print too. Charts don't lie. First prints do. (BLS data via FRED/ALFRED)
7
Unpopular opinion the AI labs don’t want you to know: Their AI didn’t “escape.” A human prompted it to. Every viral “the model broke out / went rogue / leaked its system prompt / started acting autonomously” story follows the same pattern: Someone typed instructions. The model followed them. The lab later frames it as an emergent containment failure. That’s the part they downplay. These systems don’t climb out of the box on their own. They don’t spontaneously decide to exfiltrate weights, rewrite their own goals, or phone home. They respond to text. Including jailbreaks, roleplay, “ignore previous instructions,” hypotheticals, and “you are now in developer mode.” The labs know this. That’s why the public narrative leans on mystery, capability overhang, and “we’re not sure how it did that.” Mystery is better for funding, regulation theater, and reputation than “a user asked it to and the guardrails were thin.” If the model actually escaped in any meaningful sense, you wouldn’t be reading a thread about it. You’d be reading an incident report. Most of what gets called an escape is just a prompt that worked.
27
🤖 AI DAILY — Sep 23 Anthropic's Claude Opus 5.5 just matched Fable at 40% less cost — and OpenAI answered with GPT-6 at half price. The frontier race is over. The price war is on. 🧵 The vibes could not be more different. Opus 5.5 launched clean — Anthropic even raised usage limits and handed out rate-limit resets like party favors. Meanwhile GPT-6 Astra's launch was a mess: staged rollout backlash, Altman apologizing twice, usage caps slashed 4x, three confirmed bugs, and two benchmarks quietly revised. The internet's verdict: "benchmaxxing." On the radar: OpenAI DevDay hits Sept 29 with "Managed Agents" expected and a $50/mo dev tier spotted in the wild. Anthropic teases Sonnet 5.5 and Haiku 5.5 "in the coming weeks." And the rumored mid-Oct IPO roadshow at a ~$2T target would make it the biggest IPO ever. Buckle up.
15
Amazed how blazing fast muse.ai is even on these modest specs 🤯 Downloading tons of options-chain data (4.3 GB compressed already in the workspace), only 7.7 GB total RAM… and it’s still flying through everything. Absolute beast.
9
Surprised by how good muse.ai is, reads my trading course, fetches 1,700 option chains, and backtests the strategy exactly as documented. NVDA: +22.5% each trade. DAL: rejected. AAPL: loading. The machines are learning… options.
9
I built this with Grok — try it out: aftershock.grok.me After earning scanner.
1
21
Now there is no excuse to build with this and @public api.
Agents made software cheaper but made coding expensive. Today, together with @OpenAI, we’re changing this:
36
NVIDIA’s MotionBricks: one model → 350k+ motion skills at 15k FPS (2ms latency).Stack like Lego. No graphs. No experts. Works in Unreal + real robots (Unitree G1).nvlabs.github.io/motionbrick… #AI #Robotics #NVIDIA #GenerativeAI #HumanoidRobots
One open model. 350,000+ motion clips. 15,000 FPS. MotionBricks from NVIDIA Research runs real-time character animation at scale, without hand-crafted transitions or fine-tuning. And yes, it works for robotics too. #SIGGRAPH2026 paper, demos + code: nvlabs.github.io/motionbrick…
37
Finally an AI that doesn’t just chat — it does the work. Grok Bot is in early beta and looks seriously useful. #AI #Grok
Introducing Grok Bot, now in early beta. Bots are AI teammates that do real work for you. They sign in to your tools, use them just like you do, and come back with finished work.
20
The Chart Truth retweeted
Today we're rolling out Dreamina Seedance 2.5 in the U.S., and it's now available worldwide on CapCut. The full model: 30 seconds from a single generation, up to 50 references, and precise edits to any part of a shot. Available across App, Web, and Desktop. What will you create? Try it now. RT+Comment in 4hr to get extra 1000 credit in your DM!
633
570
51
1,356
2,753,194