Given that it was literally a few months ago when these models could barely do text at all, it seems like the bar just gets higher with each advancement, no matter how impressive.
I think it's totally OK to experiment with pricing and rapidly iterate. I dropped my ChatGPT sub for Anthropic because it was great value and Claude Code was a 'game changer' product.
I hold them no ill will for rapidly changing pricing models, raising pricing, doing whatever they need to do in what must be a crazy time of finding insane PMF in such a short time
BUT the communication is basically inexcusable IMO. I don't know what I'm paying for, I don't know how much I get, their pricing and product pages have completely different information, they completely hide the fact that Opus use is restricted to the Max plan, they don't tell you how much Opus use you get, their help pages and pricing pages look they were written by an intern and pushed directly to prod. I find out about changes on Twitter/HN before I hear about them from Anthropic.
I love the Claude Code product, but Anthropic the company is definitely nudging me to go back to OpenAI.
This is also why competition is great though - if one company had a monopoly the pricing and UX would be 20x worse.
This is pretty similar to my set up but I'm ready to quit Firefox because what feels like every few weeks they somehow manage to add new auto-enabled spyware.
I regularly have to turn stuff off in
"Firefox Data Collection and Use"
and
"Website Advertising Preferences"
Recently I also started seeing ads in my address bar when typing stuff and saw they've added:
"Suggestions from sponsors
Support Firefox with occasional sponsored suggestions."
of course, enabled by default.
Firefox is a great product but unfortunately slowly being milked/destroyed by its non-technical management team.
I followed this on Twitter and it all seems a bit contrived to me, as if the guy set up the situation to go viral.
- He's a courseboi that sells a community that will make you 'Get from $0 to $100 Million in ARR'
- The stuff about 'it was during a code freeze' doesn't make sense. What does 'code freeze' even mean when you're working alone and vibe coding and asking the agent to do things
- Yes LLMs hallucinate. The guy seems smart and I guess he knows it. Yet he deliberately drives up the emotional side of everything saying that replit "fibbed" and "lied" because it created tests that didn't work.
- He had a lot of tweets saying that there was no rollback, because the LLM doesn't know about the rollback. Which is expected. He managed to rollback the database using Replit's rollback functionality[0], but still really milks the 'it deleted my production database'
- It looks like this was a thread about vibe coding daily. This was day 8. So this was an app in very early development and the 'production' database was probably the dev database?
Overall just looks like a lot of attention seeking to me.
I am also convinced that this is a contrived and fake case for the reasons you've listed. Don't get me wrong, I am super critical of the AI hype and "vibe coding" (God, I detst that term), but this just seems too "well-made".
He is not a "courseboi". SaaStr is a legit brand that's been around for a long time focusing on the sales side of SaaS.
You have to remember this is someone who is almost certainly completely non-technical and purely vibe coding. He won't know what things like code freeze, rollbacks, production database, etc actually mean in real engineering terms and he is putting his full trust in the LLM.
The "code freeze" thing was amusing, I've never used Replit so wondered if it was a feature to turn off code editing but the more you read it seems like he just told it that it was in code freeze or added it to the rules and expected it to not drop that context at some point.
The "rules" thing in LLM coding probably should be called "suggestions" because it never seems that stringent about them.
Calling Rplit Agent (the AI) just Replit is also a bit sus, as it might sound like the company itself is doing these nefarious things, while it's more like the agent doesn't understand features of the environment it is in.
I honestly just thought it was entirely fake when I saw it fly all over LinkedIn. Maybe I'm too cynical, or maybe I'm the right degree of cynical, I don't know any more.
Basically it's more about cash flow than profit. In the example, you can claim those expenses back eventually so if you survive the initial $1M hit then after the time period has passed you're back to normal.
For a small business this is astronomically harder than for Google.
Yeah this is super annoying and wish they'd fix it. I missed the asterisk and bought Claude Team for my team so they could use claude code but then saw it's excluded and had to go through a refund cycle and now they have to buy it individually.
I have airtags in my backpack, briefcase, wallet, luggage and keys now. One of the best qol improvements I've done. I'm careless and forget stuff a lot and even just saving the few minutes it regularly took me to find stuff misplaced at home is great. It also let me recover my bag when I forgot it on a train (I watched it go to a holding station overnight and travel all over the country the next day, and could then anticipate where it would be and go take it back)
I also have a similar experience to that described in the article (nearly 10 years ago, pre airtags) of having my wallet drop out my pocket while cycling in the Netherlands. A German couple found it and took it back to Germany with them as they weren't sure what to do. They found me on Facebook, asked if it was ok to take some cash from the wallet, and put it in the post back to me in NL.
Coming from South Africa which probably has similarities to Russia in terms of return rates for lost valuable belongings it was quite a defining moment of "Europe" for me.
MCP terminology is already super confusing, but this seems to just introduce "MCP Host" randomly in a way that makes no sense to me at all.
> "MCP Host": applications (like LM Studio or Claude Desktop) that can connect to MCP servers, and make their resources available to models.
I think everyone else is calling this an "MCP Client", so I'm not sure why they would want to call themselves a host - makes it sound like they are hosting MCP servers (definitely something that people are doing, even though often the server is run on the same machine as the client), when in fact they are just a client? Or am I confused?
I think host is a bad term for it though as it makes more intuitive sense for the host to host the server and the client to connect to it, especially for remote MCP servers which are probably going to become the default way of using them.
I'm with you on the confusion, it makes no sense at all to call it a host. MCP host should host the MCP server (yes, I know - that is yet a separate term).
The MCP standard seems a mess, e.g take this paragraph from here[1]
> In the Streamable HTTP transport, the server operates as an independent process that can handle multiple client connections.
Yes, obviously, that is what servers do. Also, what is "Streamable HTTP"? Comet, HTTP2, or even websockets? SSE could be a candidate, but it isn't as it says "Streamable HTTP" replaces SSE.
> This transport uses HTTP POST and GET requests.
Guys, POST and GET are verbs for HTTP protocol, TCP is the transport. I guess they could say that they use HTTP protocol, which only uses POST and GET verbs (if that is the case).
> Server can optionally make use of Server-Sent Events (SSE) to stream multiple server messages.
This would make sense if there weren't the note "This replaces the HTTP+SSE transport" right below the title.
> This permits basic MCP servers, as well as more feature-rich servers supporting streaming and server-to-client notifications and requests.
Again, how is streaming implemented (what is "Streaming HTTP")?. Also, "server-to-client .. requests"? SSE is unidirectional, so those requests are happening over secondary HTTP requests?
--
And then the 2.0.1 Security Warning seems like a blob of words on security, no reference to maybe same-origin. Also, "for local servers bind to localhost and then implement proper authentication" - are both of those together ever required? Is it worth it to even say that servers should implement proper authentication?
Anyway, reading the entire documentation one might be able to put a charitable version of the MCP puzzle together that might actually make sense. But it does seem that it isn't written by engineers, in which case I don't understand why or to whom is this written for.
> But it does seem that it isn't written by engineers
As far as I can tell, unsurprisingly, the MCP specification was written with the help of LLMs, and seemingly hasn't been carefully reviewed because as you say, a bunch of the terms have straight up wrong definitions.
Regardless if it's a RFC, standard or whatever, protocols need to be precise, exact and correct. And I think they wrote MCP with the idea of others using it, otherwise why even make it public if it's just for their own usage?
reply