201–210 of 234 posts
But if I want the Agent to do something that can't be done with commands i.e. go into Google Docs and organize all my documents, then an MVP server would make sense.
It's finally happening. The acceleration of the full AI disillusionment: - LLMs will do everything. - Shit, they won't. I'll do some traditional programming to put it on a leash. - More traditional programming. - Wait, this traditional programming thing is quite good. - I barely use LLMs now. - Man, that LLM stuff was a bad trip. See you all on the other side!
Earlier quoted context omitted.
If you use git on Windows, bash is normally available. Agree, that this isn't widely used though.
Yeah I’ve never see anyone rely on users to use GitBash to run shell scripts. Amusingly although I certainly use GitHub for hobby projects I’ve never actually used it for work. And have never come across a Windows project that mandated its use. Well, maybe one or two over the years.
Earlier quoted context omitted.
Well, with MCP you’re giving textual instructions to Claude in hopes that it correctly generates a tool call for you. It’s not like tool calls have access to some secret deterministic mode of the LLM; it’s still just text. To an LLM there’s not much difference between the list of sample commands above and the list of tool commands it would get from an MCP server. JSON and GNU-style args are very similar in structure.…
Not strictly true. The LLM provider should be running a constrained token selection based off of the json schema of the tool call. That alone makes a massive difference as you're already discarding non-valid tokens during the completion at a low level. Now, if they had a BNF Grammer for each cli tool and enforced token selection based on that, you'd be much better off than unrestrained token selection.
Earlier quoted context omitted.
Yeah I’ve never see anyone rely on users to use GitBash to run shell scripts. Amusingly although I certainly use GitHub for hobby projects I’ve never actually used it for work. And have never come across a Windows project that mandated its use. Well, maybe one or two over the years.
Lot's of Microsoft shops (majority even) use ADO which is basically github + project management. I'd say most devs targeting Windows use git in some form. If not, what are you using? If git is installed, so is git bash. So bash is basically everywhere, even on Windows. The difference is, I'd say 1/50 devs using Windows actually know this.
Even if GitBash is installed, and I’m happy to concede it is, there are a variety of hurdles. Both technical and practical. But I will concede it is technically possible.
I will however maintain that bash is not everywhere in practice. And that if you write libraries or projects that expect Windows users to run bash scripts then you’re a bad software engineer and a bad person. Don’t do that.
Integrating something that required running under GitBash would be a non-starter at my current company. That’s just not how literally anything works. So sure technically possible. But with enough effort anything is possible!
Using an LLM to count how many Rs are in the word strawberry is silly. Using it to write a script to reliably determine how many are in is not so silly.
The same goes for many repeated task you'd have an LLM naively perform.
I think that is essentially what the article is getting at, but it's got very little to do with MCP. Perhaps the author has more familiarity with "slop" MCP tools than I do.
It's finally happening. The acceleration of the full AI disillusionment: - LLMs will do everything. - Shit, they won't. I'll do some traditional programming to put it on a leash. - More traditional programming. - Wait, this traditional programming thing is quite good. - I barely use LLMs now. - Man, that LLM stuff was a bad trip. See you all on the other side!
You very much misunderstood the article (or, more likely, didn't even open it) because it fit your increasingly fringe skeptic narrative.
I misunderstood _because_ it fits my narrative? Or I didn't opened it _because_ it fits my narrative?
I think I nailed it, and the article approach is representative of the "oh shit, it can't do it all" phase, which soon will be followed by "more traditional programming".
These guys promised you an LLM that can do magic, from curing cancer to solve democracy, while delivering half-assed shit that doesn't stand scrutiny (even for the non-hype purposes it was designed for), and somehow I am the "fringe skeptic". If skeptics are on the fringe, then who is in charge of mainstream?
Earlier quoted context omitted.
>LLMs? Look more and more like the Metaverse every day as concerns the economics. ChatGPT has 800M+ weekly active users how is that comparable to the Metaverse in any way?
I said as concerns the economics. It's clearly more popular than the Oculus or whatever, but it's still a money bonfire and shows no signs of changing on that front.
In this case though I think the ChatGPT product line is profitable albeit not enough to cover the R&D costs of OpenAI.
Earlier quoted context omitted.
Off the shelf Chinese drones is somewhat vague, we can just say DJI. Their full drone and dock system for the previous generation goes for around $20k. DJI iterates on this space on a yearly cadence and have just come out with the Dock 3. 54 minute flight time (47 min hover) for fully unmanned operations. If you're talking about fpv racing where tiny drones fly around 140+ mph, then yeah DJI isn't in that space.
That hardly seems like it would take the US 10 years to replicate on a war footing aside from the price. I mean if we’re talking dollar to dollar comparison, the US will likely never be able to produce something as cheaply as China (unless China drastically increases their average standard of living).