Yesterday, OpenAI took a page out of the Anthropic playbook and announced to every journalist on Earth that their next AI model is super duper scary and dangerous. And because Sam Altman cares about your safety more than anything, he decided to hit the pause button on frontier reinforcement learning for the next 2 weeks. That's so controversial, yet so brave. And the official reason is that OpenAI's next model, codenamed Astra, may have crossed the critical cyber capability threshold. And maybe that's not too far-fetched, considering one of their models recently escaped an evaluation sandbox so it could hack hugging faces production servers to cheat on a benchmark. But not everybody is buying this story, because nobody with half a brain actually believes they're stopping the largest planned training run in history for, quote, safety. There's an unimaginable amount of power and wealth at stake in the AI race right now. And some armchair experts say this is proof that AI has plateaued, while others say it's all about regulatory capture. But perhaps the most likely theory is what's happening 6,000 miles away in China. Because coincidentally, DeepSeek just returned and released the fastest starred GitHub repo in history. In today's video, we'll take a look at DeepSeek Coder and find out if it lives up to the hype, or if it's just a cheap Temu knockoff of Claude code. It is August 20th, 2026, and you're watching The Code Report. If you know your AI history, you might remember that the entire TypeScript code base of Claude code was leaked to the internet after Anthropic accidentally shipped a 57 megabyte source map file to NPM. Anthropic is famously smug about being anti-open source and anti-open weight. So this leak was like the invisible hand of God finally clicking public repository. We analyzed Claude code's source code on this channel, and it was pretty mid. So it's not surprising to see Chinese knockoff harnesses popping up now. But wait a minute, you might be wondering, what even is a harness? Well, to get AI to write your code, you first need a model to spit out and predict tokens. That's the brain of the operation. But to do everything else, you need to strap on a harness that allows the brain to use tools, plugins, the file system, manage context, and so on. And the harness runs all these things in a loop that decides when to keep going and when to stop. The some popular harnesses are OpenAI Codex, Claude Code, Open Code, and many others. But, the Deep Seek harness takes a much different architectural approach that can be summarized in three words. Everything is a plugin. The model adapter is a plugin, the tools are plugins, even the sandbox and the UI and the while loop at the center of the coding agent itself are plugins. Or in other words, they're just ordinary packages that you can swap out with one line of YAML. And that's really cool if you're a developer because it means you have a ton of control to customize your harness in ways that are not possible on other platforms. Like instead of using the sandbox Anthropic told you was safe, you have the freedom to use a custom sandbox from some random half-assed unmaintained GitHub repo. The whole thing feels like Linux, but for AI agents. At a deeper level though, this tool is built on a paper that was released by Deep Seek about spatio-temporal composability. The general idea is that components should be hot-swappable both as dependencies in the harness and over time. And they actually built a small framework called Cordis to facilitate this plugin architecture. Now, I've used many different terrible plugin systems in my days like in WordPress and Webpack, but this paper from Deep Seek is easily the most elaborate justification I've ever seen for a plugin system. But, the big question is can the Deep Seek harness write better code than Codex or Claude Code? Well, at the same time of the release of the Deep Seek harness, they also released version 4 Pro of their flagship model along with a massive pricing increase in the API. I happen to have $20 sitting on my Deep Seek account, so let's find out if it can build a production version of Horse Tender. For this one-shot prompt, I'm using V4 Pro with the max settings, but one thing to keep in mind is that you can point any different model to this harness. It's not just limited to Deep Seek's models. The first interesting thing you'll notice is that there's different modes for running this prompt. I'm just going to go with standard mode, but there's also a minimal mode that will speed things up and a creator mode if you actually want to dive into the plugins and create your own stuff. After submitting the prompt, it immediately gets to work and as it's doing its work, we can go to this trajectory panel where you can see all the reasoning, tool calls, and results in a way that feels like a stack trace for your AI model's thinking process. So, pretty cool. And after staring at that for about 29 minutes and 58 seconds, I finally had a working application built with 2.6 million output tokens, which cost a grand total of 30 cents. It built the entire thing with Node.js and React and at first I was a little bit disappointed with the UI. You'll definitely get more spectacular results with Fable or Codex, but this DeepSeek application is still pretty solid. The swipe animation was implemented well, it has a nice chat feature, and got the job done well on a bunch of other small details. So, yeah, if I were Sam or Daria right now, I would be totally terrified and just give up on this whole AI grift. But if you want to actually understand AI issues at a deep level, you need to check out Blue.impact, the sponsor of today's video. They're a nonprofit whose mission is to get more people involved in making AI go better for humanity. The main way they do that is by offering free online courses like their future of AI course, which provides an unbiased introduction to where AI is today and where things could be heading over the next few years. They also have more technical courses on things like AI governance and biosecurity along with personalized career support for people interested in working on AI safety. All of Blue. resources are free to use because they're funded by philanthropic donations and they've helped over 8,000 people get jobs at organizations like DeepMind, Stanford HAI, and Apollo Research. Try out their future of AI course right now at the link below. This has been The Code Report. Thanks for watching and I will see you in the next one.
Generated algorithmically for Search Engine
Indexing.