Video yükleniyor...
Video Yüklenemedi
Full-circle Test-driven Firmware Development with OpenClaw Ladyada: "I've only had OpenClaw installed on this Raspberry Pi 5 for a couple of days, but boy, have we burned through a lot of tokens and learned a lot. Including what I think is a really fun improvement in my development process:... show more
25,105 görüntüleme • 4 ay önce •via X (Twitter)
0 Yorum
Yorum bulunmuyor
Orijinal gönderinin yorumları burada görünecek
![Ever since I wired Claude Code to WhatsApp 3 weeks ago, I built a stupidly large infra around it. I mean, opus built it. No clue how the code even looks. The entire thing was vibe coded using my phone. I wanted to see how far I could push it without touching the computer. Everything via WhatsApp. Build what I need on the fly. So the resulting infrastructure will already be battle tested for software development. The entire thing was streamlined with nearly no manual interventions, everything was communicated via WhatsApp using a single script establishing this connection. If the script is down, I need to get home to start it again to resume the development. Claude was upgrading it, debugging it, restarting it while maintaining constant uptime so it could keep communicating with me. I stressed Claude about it, telling it that it will be “in the dark” and other words that deliberately sound scary about losing communications if the script dies. I also refused git and refused cloning the code, I wanted to see Claude adapting to work on a *LIVING* system. The way this whole thing works: Claude has its own dedicated phone number that I am paying for. A real WhatsApp account for it is installed on a real iPhone that is sitting on my desk. All is registered under my name, this is legit setup with no hacks and tricks. I’ve set up a WhatsApp “Community” and multiple different groups under it. Both me and Claude are the admins, so Claude could edit it on my behalf. Each group is a project I am working on and has its own isolated context. The Group description is a system prompt that gets auto-appended to the larger system prompt explaining this setup in general. When I send a message it’s an instant interrupt to Claude Code’s process, just like in the terminal. Voice notes are seamlessly transcribed with a local Whisper model. Images are used with multimodal reading in an isolated parallel session. Multiple groups running in parallel so I can work on all projects at the same time. No cross-talking, everything has an isolated context and history. And because it’s local on my own machine: Everything is REAL. The browser is REAL. I am connected as myself on it to all services because I actually use it in real life. Claude has unlimited internet access, just like humans who use actual browsers. It utilizes custom-made browser tools that I made to control any browser session it wants. Depending on the situation, it can either connect to my existing session or create one for its own. (You can tell it ‘look at my browser for a sec’ then talk about the current page you are on and it just works, pretty cool) My custom browser tools are not perfect (not by a long shot) but I managed to make them work well to the point they are somewhat reliable. This gives Claude full access to my real creds and all the services I actually use. I’m productive AS HELL with this. It really feels like a personal assistant. I ask it to read my emails and msgs, check x .com for news, research arxiv papers, write code, run experiments for me, investigate and reverse engineer github repos, even use my credit card and order things. [I try not to do this one a lot lol so far no disasters]. All from my phone. Super convenient. This is not a product or an open source project (maybe soon of it will make sense). This is just an ugly script I hacked the entire thing is ~600 lines. (ok maybe i did look at the code, but i swear i didn’t edit!) You can also vibe code this from scratch pretty fast and it will probably even end up better. This is just a cool thing so I’m sharing. It is a real speed booster for many things I do on daily basis, mostly boring things. Forcing my routine into some new “agent platform” just didn’t feel right for me. WhatsApp is where I already communicate and look for messages, so I decided that my agents will live there too. AGI in my pocket 24/7.](https://image.24vids.com/tw-2000642897402880491/amplify_video_thumb/2000642716951064582/img/ReuTixQFFAAQc_x0.jpg)
![The most interesting part for me is where Andrej Karpathy describes why LLMs aren't able to learn like humans. As you would expect, he comes up with a wonderfully evocative phrase to describe RL: “sucking supervision bits through a straw.” A single end reward gets broadcast across every token in a successful trajectory, upweighting even wrong or irrelevant turns that lead to the right answer. > “Humans don't use reinforcement learning, as I've said before. I think they do something different. Reinforcement learning is a lot worse than the average person thinks. Reinforcement learning is terrible. It just so happens that everything that we had before is much worse.” So what do humans do instead? > “The book I’m reading is a set of prompts for me to do synthetic data generation. It's by manipulating that information that you actually gain that knowledge. We have no equivalent of that with LLMs; they don't really do that.” > “I'd love to see during pretraining some kind of a stage where the model thinks through the material and tries to reconcile it with what it already knows. There's no equivalent of any of this. This is all research.” Why can’t we just add this training to LLMs today? > “There are very subtle, hard to understand reasons why it's not trivial. If I just give synthetic generation of the model thinking about a book, you look at it and you're like, 'This looks great. Why can't I train on it?' You could try, but the model will actually get much worse if you continue trying.” > “Say we have a chapter of a book and I ask an LLM to think about it. It will give you something that looks very reasonable. But if I ask it 10 times, you'll notice that all of them are the same.” > “You're not getting the richness and the diversity and the entropy from these models as you would get from humans. How do you get synthetic data generation to work despite the collapse and while maintaining the entropy? It is a research problem.” How do humans get around model collapse? > “These analogies are surprisingly good. Humans collapse during the course of their lives. Children haven't overfit yet. They will say stuff that will shock you. Because they're not yet collapsed. But we [adults] are collapsed. We end up revisiting the same thoughts, we end up saying more and more of the same stuff, the learning rates go down, the collapse continues to get worse, and then everything deteriorates.” In fact, there’s an interesting paper arguing that dreaming evolved to assist generalization, and resist overfitting to daily learning - look up The Overfitted Brain by Erik Hoel. I asked Karpathy: Isn’t it interesting that humans learn best at a part of their lives (childhood) whose actual details they completely forget, adults still learn really well but have terrible memory about the particulars of the things they read or watch, and LLMs can memorize arbitrary details about text that no human could but are currently pretty bad at generalization? > “[Fallible human memory] is a feature, not a bug, because it forces you to only learn the generalizable components. LLMs are distracted by all the memory that they have of the pre-trained documents. That's why when I talk about the cognitive core, I actually want to remove the memory. I'd love to have them have less memory so that they have to look things up and they only maintain the algorithms for thought, and the idea of an experiment, and all this cognitive glue for acting.”](https://image.24vids.com/tw-1979259041013731752/amplify_video_thumb/1979257571786543104/img/OqUh56yit9gUQWnb.jpg)
![REMINDER: The genome for SARS-CoV-2 is a "consensus sequence." Anybody who says the gene sequence for SARS2 is confirmed is *confused or lying.* "[The reality is that] nobody has the code of the pathogen..." "What they set for the control [for the PCR 'test'] is a consensus sequence, which [means] they took AI, they averaged out a section of the genome that they want as that test, and they set it for that. So it doesn't even exist in nature anywhere." This is a clip from a recent discussion between former medical coder and whistleblower Zowe Smith (Zowe Smith) and retired pharma R&D executive Sasha Latypova (sashalatypova.substack.com "Due Diligence and Art"). Smith and Latypova discuss the many shortcomings of PCR "tests," as well as the fact that no genome for SARS-CoV-2 has ever been characterized—only a "consensus sequence," which Smith notes is developed when AI "average[s] out... a section of the genome that they want as a test." She adds, "it doesn't even exist in nature anywhere." Latypova confirms, "when they're saying, 'Oh, we have the COVID virus, the full genome...it's been sequenced. Look at all these papers.' [The reality is that] nobody has the code of the pathogen... Ralph Baric also wrote about it in his work all the time. So nobody has the pathogenic sequence." The pharma insider adds, "What they upload to GenBank is... averaged... And once it's averaged, it's no longer pathogenic anything. It's just a model. And then for PCR, [it] doesn't test the full genome. They do these, like, snippets, and then whatever snippet you wanna set it to, you will find it, and that's how they find... positive COVID. So all of this is total BS." Interestingly, Smith notes that when she worked with PCR in a lab at the Oregon Health and Science University "[she] realized that everything was controlled through EUA [Emergency Use Authorization] and the CDC, so there was no way to independently verify [the controls that were used]."](https://image.24vids.com/tw-1901334053984301146/ext_tw_video_thumb/1901324611528130560/pu/img/Wzq8QVj_6y--8AxD.jpg)
