looks like it’s Planetary now https://apps.apple.com/us/app/planetary-social/id1481617318
looks like it’s Planetary now https://apps.apple.com/us/app/planetary-social/id1481617318
The big difference with R1 at least is that it is trained using reinforcement learning, and it gives you an explanation of how it arrived at a solution. I find the thinking bit is really fascinating cause it really reads like a train of thought. Here’s an example of what it outputs when I ask it to write a react component with a text input and a button:
<think> Alright, the user asked for a React component that includes a text input and a button. I need to write this in a way that’s clear and functional.
First, I’ll start by setting up the basic structure of a React component. I’ll import React and useState since we’ll need state management for the input value.
Next, I’ll create a functional component called TextInputButton. Inside this component, I’ll use the useState hook to manage the text input’s value. The initial state can be an empty string.
Then, I’ll define a handler function, handleChange, that updates the state whenever the user types into the input. This function will take the event object and set the new value using setTextInputValue.
I also need a function to handle the button click. For now, I’ll use handleClick with an alert message as a placeholder. The actual functionality can be added later based on requirements.
In the return statement, I’ll structure the JSX. I’ll include an input element of type text, binding its value to the state variable and attaching the handleChange function to the onChange event. This ensures that the state always reflects the current input value.
Below the input, I’ll add a button element. On clicking this button, it will trigger handleClick. I’ll also give it a class for styling purposes, like ‘button’ which can be styled with CSS if needed.
Finally, I’ll export the component so it can be used elsewhere in the application. I’ll make sure to include comments explaining each part for clarity. </think>
Here’s a simple React component with a text input and a button:
import React from 'react';
import { useState } from 'react';
function TextInputButton() {
const [text, setText] = useState('');
const handleChange = (event) => {
setText(event.target.value);
};
const handleClick = () => {
// Add your click handler logic here
alert('Button clicked!');
};
return (
<div>
<input
type="text"
value={text}
onChange={handleChange}
placeholder="Enter text..."
/>
<button onClick={handleClick}>Submit</button>
</div>
);
}
export default TextInputButton;
This component:
You can use this component in your application like:
<TextInputButton />
The input value is controlled through the text
state variable, and you can access it using text
. When the button is clicked, the handleClick
function will execute whatever logic you need.
As I explained above the open source models aren’t the problem from the US perspective. DeepSeek will obviously continue to release models, and it will likely become the standard outside the west. However, US will not allow it become the dominant service provider in the US, and that’s why I expect the service to be banned. The US will force American companies to use a domestic provider, and Europe is likely to do the same.
The key for them is that they want the service to be provided by a US company. There are actually already a few companies hosting DeepSeek in US, and I’m sure the techniques will be incorporated by everyone in short order.
If you can get by with the apps available for it then could work. I use LineageOS on my phone and it works pretty well.
I can’t see Google abandoning Android, but they might kill Pixel.
Exactly, and these kinds of policies will only ensure that the west starts falling behind technologically. Stifling innovation to prop up monopolies will not be a winning strategy in the long run.
I haven’t actually used that one, but doesn’t the same point apply here too? The whole point of DeepSeek is in distillation that makes runtime requirements smaller.
They’re gonna ban access to the official service provided by a Chinese company. That’s what this is about. The biggest fear is that everybody starts using DeepSeek, and then it will muscle out US companies that fell behind. Once people start using their service, they’ll have little reason to switch to something else going forward. Banning it is a protectionist measure that allows US companies to catch up.
What they’re actually in panic over is companies using a Chinese service instead of US ones. The threat here is that DeepSeek becomes the standard that everyone uses, and it would become entrenched. At that point nobody would want to switch to US services.
Not exactly an option against a nuclear superpower with a far bigger industry than Yankeestan. What’s most likely to happen is that the west will simply isolate itself from the rest of the world and will continue to fall further behind technologically. It’s going to be a hermit kingdom of the G7.
The main difference is speed and memory usage. Qwen is a full-sized, high-parameter model while qwen-distill is a smaller model created using knowledge distillation to mimic qwen’s outputs. If you have the resources to run qwen fast then I’d just go with that.
still going strong
I’m running deepseek-r1:14b-qwen-distill-fp16 locally and it produces really good results I find. Like yeah it’s a reduced version of the online one, but it’s still far better than anything else I’ve tried running locally.
you’d just join one of the pub servers here I think https://github.com/ssbc/ssb-server/wiki/Pub-Servers
Oh haha no, just sharing cause it’s a neat idea.
The Silo is a fun show, the book series it’s based on is really good too.
Because you’re a debate bro who wastes other people’s time arguing about subjects you have no clue about. If you want people to take you seriously spend a bit time educating yourself instead of speaking out of ignorance.
Study after study shows that China’s involvement in Africa has measurable positive impact, but here you are with your wikipedia link acting like you have a clue
ah I haven’t kept up