Been through this 3 times in the last 6 months. They're getting better. Very credible LI profiles, code looks OK if you only take a glance... The bell start ringing when they insist you to run locally their sh*t
Is anyone able to actually use this? I've set it up in opencoder, tried a few times, at various hours. Invariably, I end up with a timeout and an error message in Chinese.
That is a very good start in sharing some level of information with their users, and kudos to the Anthropic team for doing that. However, I don't see any mention of the longstanding issue in CC of API timeout errors. And, at least for me, it's the most frustrating one.
Maybe I'm missing something, but going through the docs I can see how to register agents, create sessions, etc. What I don't see is a "minor" thing, how can I store a memory and how I can query the server for memories. What am I missing?
Have you ever tried to use it? Because I fought for about 2 months with both Google and Microsoft, trying to self-host my mail server, to no success. The only answer was amongst the lines 'your server has not enough reputation'. Even though perfectly configured, DKIM, DMARC, etc. Now imagine a business not being able to send a message to anyone hosted on Gmail or Outlook, probably 80-90 percents of the companies out there.
Gemini for sure, in my experience. I asked 2.5 (presumably the most advanced in the known Universe) to write some code. First it came back with suggestions on HOW to write that code. Asked again. He wrote some, but from 4 functions implemented, 2 were just comments explaining again how to implement that function. Notable mention, one of them was supposed to call the Gemini API. Everything Python, nothing fancy. Took me like 6 rounds of back and forth until I got some very basic structure... So, no vibe coding with Gemini for me.
First, I would recommend to add some pricing guidelines, I presume the service won't be free. I would not expect definitive commitments, but will it be o1-pro pricing or Deepseek pricing? Second, tried to sign up with my google account, google said app was blocked because it tried to access sensitive information. So...
Once you have the OpenAPI specs, you can build an MCP server on top of that. Automatically. You don't have them ? There's MITM2Swagger[0] that will do it's best to infer it. Probably you'll need some manual adjustments, but still. And MCP servers can now be integrated with any LLM, not only Anthropic. While I appreciate your approach, how do you fight the MCPs?