News for hackers. Stuff that matters.

tb1989

Re:OpenAI adds MCP support to Agents SDK on Wednesday March 26, 2025 @05:20PM (#43487436)
I prefer this interpretation:

MCP Isn’t the USB-C of AI — It’s Just a USB-C(laude) Dongle

https://dev.to/internationale/mcp-is-not-ai-usb-c-its-usb-cl...

The illustrations are on their official website.

I find it hard to respect a company that invented dongle and claims to have invented USB

I totally agree. As someone with an EE background, this metaphor makes me a little physically uncomfortable. Considering that the developers and users of mcp are almost all programmers who need to use cli, I really don't understand why they don't tell the truth to programmers.
- The official example strongly promotes the Anthropic API, which is on GitHub. This is clear evidence.

- There is no clear explanation of the coupling between the system prompt and the tool call. Even if it mentions the open source Gemma or Deepseek, it would be much better.

The official attitude makes it difficult to trust this project.

The point you made is exactly the cunning part. Anyone can copy it, but without official support, it is simply impossible: this is pure community exploitation

I think this article explains it all:

MCP Isn’t the USB-C of AI — It’s Just a USB-Claude Dongle

https://dev.to/internationale/mcp-is-not-ai-usb-c-its-usb-cl...

Nonetheless, I think your work is very good and it looks like a very useful dongle

Re:Ask HN: What's Your Opinion on MCP? on Sunday March 23, 2025 @10:14AM (#43453066)
Frankly speaking, labeling MCP as "USB-C for AI" is an exaggerated metaphor. USB-C is a universal standard driven by IEEE and the open-source community, while MCP is fundamentally an ecosystem tightly controlled by Anthropic itself. Despite adopting the MIT license, MCP is far from the spirit of genuine openness. For instance, the official examples exclusively utilize Anthropic’s own API, and the system prompt of LLM requests is hidden within their SDK—precisely the part that's crucial for openness.

Anthropic has historically been cautious, even conservative, regarding open source. They refuse to open-source Claude's CLI and the underlying model code, which makes their sudden enthusiasm for launching MCP, presented as an "open platform," rather puzzling. Is this openness genuinely for the community, or merely an attempt to benefit their own ecosystem and interests?

In reality, MCP is more like a clunky dongle that awkwardly connects HDMI or TF card readers specifically to their own models, rather than establishing a genuinely universal standard. It's nearly impossible for MCP to change the conventional methods of using APIs and authentication into an "AI-native" approach. Due to security considerations, this design inherently caps the potential of both agents and MCP itself.

For developers, MCP imposes high environmental prerequisites, like Python, Node, or Docker, virtually excluding non-technical users. The installation process is the opposite of elegant.

In the long run, this superficially open yet fundamentally closed approach is unlikely to win sustained community trust or long-term success. Security concerns, the allocation of community benefits, and the inherently closed mindset of the corporation are critical issues that will inevitably haunt MCP’s future development.

Calling MCP "USB-C for AI" feels more like marketing hype than technological reality.

Re:A Deep Dive into MCP and the Future of AI Tooling on Sunday March 23, 2025 @08:48AM (#43452538)
I feel that calling it the AI tooling of the future is an exaggeration:

https://dev.to/internationale/the-mcp-trap-is-the-open-sourc...

Re:Show HN: A free alternative to Typora –– IF on Sunday October 13, 2024 @03:20AM (#41825889)
Bro, this way of thinking of presuming others guilty is very primitive...Disclosure is very important! If you want to sell products overseas outside of mainland China, you must know this.
This value is very Chinese. But in the long run, lack of morality will only be harmful to the economy.
this 'grifter' is on TE's board, so things are out of control
Re:Insta360 has been Hiding Sponsorships on Monday May 27, 2024 @01:37PM (#40492885)
Tell me one thing, not all (100%) AI companies are scammers, but all Internet scammers will definitely say that they are engaged in AI.
Re:Cracked Rabbit R1 APKs running on Android phone on Wednesday May 01, 2024 @03:45PM (#40228389)
an iphone + korg nano series 2 :)
Re:Cracked Rabbit R1 APKs running on Android phone on Wednesday May 01, 2024 @02:52PM (#40227616)
Apparently, TE knows this Rabbit person's background as we are talking about millions dollar business. TE's values here are questionable when they decide to go with this guy.

As for OP1, packaging a tape effect when it can't produce good sound quality is a fraud. Sampling from FM? Check Klaus Schulze.. Music startups can certainly innovate, such as Roli (Seaboard and Rise), moog. make noise. Open source monome. and, to my sorrow, Émilie Gillet (Mutable Instruments). TE's innovation in music itself is far inferior to them. If you praise te, I think it is unfair to other people who are obsessed with technological innovation.

I have always felt that TE is a electronics company with no innovation in hardcore technology. The appearance and packaging are different from previous ones, but there is not enough practical integration. Of course, this is just my personal opinion. If you disagree, you can write down your opinion. Thank you.

Re:Cracked Rabbit R1 APKs running on Android phone on Wednesday May 01, 2024 @12:26PM (#40225478)
as innovative as rabbit r1
Re:Cracked Rabbit R1 APKs running on Android phone on Wednesday May 01, 2024 @10:12AM (#40223506)
Doesn't surprise me. In my opinion, many companies try to achieve outrageous premiums by taking the route of teen engineering (the originator of hype). In addition to rabbit, there is also a series of nothing products.

This doesn't convince the tech fetishists. In fact, I think te's contribution to music is very limited, even harmful, especially when I see the latest Yamaha even imitating te, which feels a bit funny and ridiculous. We need real innovation and democratic pricing.

By the way, if you care, you can learn about the history of rabbit’s founder. Let's just say, in certain circles, this is a recognized liar. So I’m not surprised at all when it was said a few days ago that Rabbit stole everyone’s passwords.

Re:Liu Cixin's War of the Worlds (2019) on Monday April 29, 2024 @03:45PM (#40203184)
you are right. But what I mean is that there is no need to make exaggerated reports, but it should be discussed from the perspective of the Chinese government's serious violations of laws and human rights, even if the Chinese government will argue that "this is my internal affairs." Exaggerated reporting is a barbaric and dishonest act that does nothing to solve the problem and prevents the public from understanding the true context of the matter.
Re:Liu Cixin's War of the Worlds (2019) on Monday April 29, 2024 @03:41PM (#40203106)
Yes. In fact, Liu's Chinese writing level is far lower than the average Chinese writer. In the original Chinese version, there are actually many words that are offensive to female (this is understandable considering his Chinese background and age). But as far as I know, these are optimized in translation. So his imagination is better amplified.
Re:Liu Cixin's War of the Worlds (2019) on Monday April 29, 2024 @03:02PM (#40202511)
I don't like Liu Cixin's novels, and I can't even read them. Because his writing style is so poor and very wordy, there are almost no golden sentences. But his plot imagination is outstanding, and I liked it very much after it was adapted into a TV movie.

His political leanings are clear. Of course, when asked about Xinjiang, his reply can hardly be used as a criterion for whether he has been brainwashed. If he publicly said this in China in the way that Westerners think he has been "brainwashed", he would have been arrested. Even if you said that Xinjiang was "re-education and vocational training" according to the official statement, you would have been arrested and banned because you It simply means "you shouldn't know about this, and you shouldn't comment on it." Even Chinese people abroad are worried about whether their family members at home will be affected.

However, many media reported very irresponsibly that before this so-called "concentration camp", Xinjiang was a matter of great concern for one's own safety. I think if you can’t live in Baghdad for a while, there is no need to comment on Xinjiang. Secondly, I think there is no direct evidence of any massacre or even death in the "concentration camp". Seeing the media reports makes people feel sad. Even videos can be faked: a typical example that comes to mind is during the Hong Kong protests in 2019, when the BBC used video to record a policeman shooting at protesters. But the whole process was about this young man trying to snatch the policeman's gun, and media outlets like the BBC actually cut the whole story off. Back to Xinjiang, in my opinion, to overuse the word "concentration camp" is to disrespect the tragic dead of World War II. The key point is that, arresting a person without trial just because he/she "appears" to have criminal tendencies.

But so what if there is procedural justice? Putin changes the law with each move. Hong Kong has revised its national security law. The United States also robbed TikTok within the legal framework because of economic interests.

I just feel that it is very tragic if a person cannot choose his own nationality and destiny. The really miserable people, such as North Koreans and many Chinese, if you are willing to help them, you should say no to the visa system and let the national borders cease to exist.

In fact, this is Liu's political view: Aliens will only be disappointed when they see us as a species that robs and kills each other. form national boundaries based on race, and then builds walls in the name of civilization after robbing. Maybe only a little part of art and science would interest aliens.

---

oops, it seems I have caused some people pain by telling the truth. Just cheaply dislike without being able to write a convincing reply.