Jonathan Cachat, PhD (@jcachat) header
Jonathan Cachat, PhD (@jcachat) profile picture

psychopharmacologist / neuroscience (phd) turned dir of data science & MLops, GCP data engineer solving mysteries without any clues

Ohio 440 & 614
Joined February 2009
Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)Photo by Jonathan Cachat, PhD (@jcachat)
Jonathan Cachat, PhD retweeted
This is f*cking insane. Andrej Karpathy: "Prompting is going away. Delete everything, keep Graph." In just 69 minutes, he breaks down how to build graphs and why they're the only layer that makes it to the end Prompts → Agents → Loops → Graphs a loop keeps one agent on the task until it's finished a graph decides which agents exist and what each one passes along to the next anyone can make an agent, almost nobody builds the graph that runs them watch it today, then save the full guide on graphs below before it goes mainstream ↓
Harness, loop and graph could be the missing layers between AI models and agents that actually work. Same model, same prompt, completely different results. In this article, I show you how to build all three layers.
12
57
547
69,676
. @kevinrose is @digg ios app dead? I can log-in on laptop, but iOS just says "network activity failed" after putting email into login field - though it does say "Create an account" rather than "login" - hoping to use @digg on mobile
38
Jonathan Cachat, PhD retweeted
Best article explaining main steps to master AI using
19
76
15
547
1,040,621
Jonathan Cachat, PhD retweeted
19 year old Japanese student built a trading bot with Claude Code in 2 days. Used his iPad as a second monitor. First night: $6,732 profit. Starting capital: $68. Total profit so far: $750,000. [ 𝐍𝐨𝐭𝐞: 𝐅𝐨𝐥𝐥𝐨𝐰 𝐌𝐞 @TechElyra 𝐅𝐨𝐫 𝐢𝐧𝐬𝐭𝐚𝐧𝐭𝐥𝐲 𝐚𝐮𝐭𝐨 𝐃𝐌] Here's how it works👇 The bot scans over 50 markets simultaneously. Syncs live BTC data from Binance every second. Spots price errors before humans even notice. The edge is pure speed + pattern recognition. While traders stare at charts trying to predict the next move, his bot is already executing on mispricing across dozens of markets. No guessing. No emotions. No hesitation. Just Claude Code logic finding gaps that close in seconds. He built the entire system in 48 hours: → Claude Code handles the trading logic → Binance API feeds real-time BTC data → iPad displays multi-market monitoring → Executes trades when arbitrage windows open The system runs 24/7. Every price dislocation = profit opportunity. Most people are still trading manually, refreshing charts, second-guessing entries. Meanwhile this 19 year old engineering student turned $68 into $750K by letting Claude Code do what humans can't: process 50 markets instantly and execute without fear. Why are people still trading manually? I'm giving away the exact Claude Code setup for free. 24 hours only. To get it 👇 1️⃣ Comment " Claude " 2️⃣ Like and Repost 3️⃣ Follow @TechElyra (so I can send it via DM)
150
111
3
280
30,924
Jonathan Cachat, PhD retweeted
An Anthropic engineer explains why he earns $350K–$950K: “I know how to build harnesses. 99% of people still build multi-agent systems manually and wonder why they keep breaking. I build systems that run loops, use sandboxed tools, and turn yesterday’s logs into new skills. Same model. 10x more reliable agents that improve while you sleep.” Opus 5.5 → Agents → Harnesses → Loops → Graphs In a short workshop, he breaks down how to build one from scratch: Step 1 → Manage loops, context, and sandboxing through a harness Step 2 → Separate the brain from the tools to reach the first token 60% faster Step 3 → Run agents server-side and recover from crashes using logs Step 4 → Make failures recoverable with retries and replays instead of starting over Step 5 → Turn past execution logs into new memories so the system gets smarter over time Anthropic calls this process “dreaming.” Most developers spend weeks building these systems manually. This workshop shows you a faster way. Bookmark this and watch it.
121
256
7
2,654
434,398
Jonathan Cachat, PhD retweeted
🚨Anthropic recently showed a 24-minute workshop on how to actually do prompts for Claude. Taught by the people who built it. Free. No registration. No paywall. I've seen $300 courses that don't cover what they teach in the first 8 minutes. Watch it and bookmark it now.
24
279
6
1,856
392,452
in honor of his 100th birthday - global treasure @ David Attenborough - one i haven't seen before, but is worth the watch 😎Shines a Light on Glowing Animals | 🤓 youtu.be/mqZDHb_eQlY?si=KVAS…
1
109
Jonathan Cachat, PhD retweeted
Google DeepMind researcher argues that LLMs can never be conscious, not in 10 years or 100 years. "Expecting an algorithmic description to instantiate the quality it maps is like expecting the mathematical formula of gravity to physically exert weight."
327
3,550
1,120
28,343
4,978,225
Revisiting my consilience via cross-pollination of intellectual history, paralleled with human migration patterns github.com/cachatj/DMoHN-int… web.archive.org/web/20130202… looking at Google's recent improvements to maps studio 👀
23
looking for the primary take-aways from #AIEngineering conf this past week in London, check out @altryne summary below 👏👏😎
Our world is changing. I spent the last week listening to, chatting, dining, dancing with and interviewing the top AI Engineers in the world all gathered in London. Here are the top 8 themes that emerged (a sneak from my upcoming blog covering the event in full 👇)
1
46
Jonathan Cachat, PhD retweeted
The math on this project should mass-humble every AI lab on the planet. 1 cubic millimeter. One-millionth of a human brain. Harvard and Google spent 10 years mapping it. The imaging alone took 326 days. They sliced the tissue into 5,000 wafers each 30 nanometers thick, ran them through a $6 million electron microscope, then needed Google’s ML models to stitch the 3D reconstruction because no human team could process the output. The result: 57,000 cells, 150 million synapses, 230 millimeters of blood vessels, compressed into 1.4 petabytes of raw data. For context, 1.4 petabytes is roughly 1.4 million gigabytes. From a speck smaller than a grain of rice. Now scale that. The full human brain is one million times larger. Mapping the whole thing at this resolution would produce approximately 1.4 zettabytes of data. That’s roughly equal to all the data generated on Earth in a single year. The storage alone would cost an estimated $50 billion and require a 140-acre data center, which would make it the largest on the planet. And they found things textbooks don’t contain. One neuron had over 5,000 connection points. Some axons had coiled themselves into tight whorls for completely unknown reasons. Pairs of cell clusters grew in mirror images of each other. Jeff Lichtman, the Harvard lead, said there’s “a chasm between what we already know and what we need to know.” This is why the next step isn’t a human brain. It’s a mouse hippocampus, 10 cubic millimeters, over the next five years. Because even a mouse brain is 1,000x larger than what they just mapped, and the full mouse connectome is the proof of concept before anyone attempts the human one. We’re building AI systems that loosely mimic neural networks while still unable to fully read the wiring diagram of a single cubic millimeter of the thing we’re trying to imitate. The original is 1.4 petabytes per millionth of its volume. Every AI model on Earth fits in a fraction of that. The brain runs on 20 watts and fits in your skull. The data center required to merely describe one-millionth of it would span 140 acres.
🚨: Scientists mapped 1 mm³ of a human brain ─ less than a grain of rice ─ and a microscopic cosmos appeared.
1,131
11,595
1,385
62,539
4,637,905
. @demishassabis - how far are we from using #projectGenie w Apple Video Pro?? @GoogleDeepMind is there opportunity for indie devs to make this integration happen, or are war chests of Google & Apple already on this?? no one wants to get Sherlock'd, but I want to build this
34
this is the coolest look into our futures with holodeck there is - unbelievable & only going to get better from here
Step inside Project Genie: our experimental research prototype that lets you create, edit, and explore virtual worlds. 🌎
1
43
when this gets connected to Apple Vision Pro - it's over!
1
26
two of the best visuals of 2025 #devops v #mlops v #llmops then the actual math behind "it just predicts the next word"
This Post is from a suspended account. Learn more
1
63
Jonathan Cachat, PhD retweeted
I built a Claude skill that turns Claude Code into your personal coding tutor. The core insight: Claude Opus 4.5 is already the best tutor in the world. @AnthropicAI cooked with this model! It has incredible emotional intelligence and deep coding knowledge. What this skill does is just provide a harness—a way for Claude to agentically build the right context about YOU so it can personalize the tutoring experience in exactly the right way. Here's what makes it work: Learner profile from day one. The first time you use it, Claude interviews you. It asks about your programming background, your goal (where do you want this to take you?), and who you are as a person. This gets saved and informs every single tutorial it ever writes for you. From the very first interaction, everything is 100% personalized. Tutorials that use YOUR code. When you ask to learn something, Claude doesn't give you generic examples from some blog post. It finds examples in the actual codebase you're working in. This makes concepts stick in a way abstract examples never do. Quiz mode with spaced repetition. You can run "/quiz-me" and Claude will test you on concepts you've learned. It tracks your understanding score for each tutorial. Then it uses spaced repetition to prioritize the next quiz—concepts you're shaky on come back in 2 days, concepts you've mastered fade to 55+ day intervals. It literally builds retention into the learning process. One central knowledge base across all your projects. Whether you're joining a new company and want to understand their codebase, learning from an open source project, or leveling up on your own vibe-coded project—all your tutorials live in one place (~/coding-tutor-tutorials/). So your personal coding-tutor accompanies you across all your coding adventures. The whole thing is a feedback loop: learn → quiz → retain → learn more → quiz → retain. Your tutorials evolve, your knowledge compounds, and Claude gets better at teaching YOU specifically over time. To install it in Claude Code: • Run /plugin to open the plugin manager • Add marketplace nityeshaga/claude-code-essentials • Enable coding-tutor plugin Here's the Github: github.com/nityeshaga/claude… And here's 20-mins of me walking you through how to use this plugin and how it works 👇🏽 Let me know if you use it to teach yourself something cool!
22
81
6
793
64,777