But LLM can write code that can do math and count. Tool use, more broadly, has proven to be a very powerful way to let LLMs do what they're good at (handle the fuzzy and imprecise nuances of natural language, which includes the scooping of a lot of context) and delegate other things they're not good at to external tools, some of which if can write on the spot.
If you think about it, we humans do that all the time too.
I'm crap at 4 digit multiplication in my head, but I have no problem doing that with pencil and paper
Fair enough, there _could_ be powerful models that are hidden from the general public, but I wouldn't call it "naive" to think the current capitalistic incentives are such that the only way to produce such models is to do exactly what we see out in the open with a handful of companies each trying their hardest to outcompete the other
You, and the HN users, `lojban`, `klingon`, `ido`, `brithenig`, `solresol`, `babm`, and `tokipona`, may want to start a club. Amusingly, nobody seems to have registered the `esperanto`, `volapuk`, `interslavic`, `balaibalan`, and `dothraki` usernames.
Italy is no Denmark but you still require to register before selling you scrap copper.
I think it's a reasonable response for a real problem and refusing to do this due to some idealistic free market principle appears to me to be a sign of fanaticism.
Can an MCP provide prompts for your model to download and use CLIs (and ensure they have the right versions of those tools) in such a way that the data flows through the client side tools?
The more I read this thread the more I'm convinced that the main value of MCP is to provide a server managed release process. This is the same advantage that SaaS has over client side apps.
However MCPs couples with a client willing to run tools locally can provide the best of both worlds
As far as I know, the only way an MCP can provide you data that doesn't go into the context is by providing URLs to the data, and then the model uses e.g. curl to access that data for data manipulation purposes. You could also return result set ids and provide accessors to such data, but ultimately you'd need to provide powerful accessors to that result set to avoid polluting context. Things like shell with all its power already provides.
It seems like there's little point in MCP in that case. Maybe more point if it was a standard mechanism for MCP to provide additional data, in a completely compatible fashion with all other tools? You could perhaps even pass such URLs to other MCPs. You could have an MCP for jq for doing stream processing. Starts to look a lot like a shell, though.
Seems like MCPs could also be extended to store auxiliary data to your memory (or filesystem..), and then an additional extension to provide that kind of data as auxiliary data in the calls to MCP.
Well, even as is, MCP still provides a standard method of using OAuth for accessing such services. And you must use MCP if you wish to add something to the ChatGPT.com web service, so it's easy to see why OpenAI folks are seeing companies going that way.
Possibly. But otoh one cannot complain that agents don't produce high quality code while at the same time not allowing them to thoroughly go through all the steps required to produce high quality code
A local director of a gold mine here in Tanzania told me that all the profits of the mine go to the owners in China. I don't know how much profit they are making, but if Tanzania as a country does not benefit from the mines then the deal is better than it should be.
If you think about it, we humans do that all the time too.
I'm crap at 4 digit multiplication in my head, but I have no problem doing that with pencil and paper
reply