Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Advanced Tool Use

anthropic.com

Post reply on HN
Print view View original

51–60 of 280 posts

Re: Claude Advanced Tool Use

#51

Post by michaelanckaert »

mkagenius wrote: post #47
michaelanckaert wrote: post #37

Earlier quoted context omitted.

I was referring to letting LLM's search github and run tools from there. That's like randomly searching the internet for code snippets and blindly running them on your production machine.

For that, we need sandboxes to run the code in an isolated environment.

Sure to protect your machine, but what about data security? Do I want to allow unknown code to be run on my private/corporate data?

Sandbox all you want but sooner or later your data can be exfiltrated. My point is giving an LLM unrestricted access to random code that can be run is a bad idea. Curate carefully is my approach.

Re: Claude Advanced Tool Use

#53

Post by kspacewalk2 »

awesome_dude wrote: post #50
wrs wrote: post #45

Earlier quoted context omitted.

It doesn’t actually require that second part. Every time I’ve used it in a production system, we had an approved list of query shapes that were accepted. If the client wanted to use a new kind of query, it was performance tested and sometimes needed to be optimized before approval for use. If you open it up for any possible query, then give that to uncontrolled clients, it’s a recipe for disaster.

Without wishing to take part in a pile on - I am wondering why you're using graphql if you are kneecapping it and restricting it to set queries.

Probably for one of the reasons graphql was created in the first place - accomplish a set of fairly complex operations using one rather than a multitude of API calls. The set can be "everything" or it can be "this well-defined subset".

Re: Claude Advanced Tool Use

#54

Post by _ea1k »

jameslk wrote: post #13

> Tool Search Tool, which allows Claude to use search tools to access thousands of tools without consuming its context window At some point, you run into the problem of having many tools that can accomplish the same task. Then you need a tool search engine, which helps you find the most relevant tool for your search keywords. But tool makers start to abuse Tool Engine Optimization (TEO) techniques to push their tools…

We just need another tool for ranking tools via ToolRank. We'll crowdsource the ranking from a combination of user responses to the agents themselves as well as a council of LLM tool rankers.

Re: Claude Advanced Tool Use

#55

Post by morelandjs »

Their tool code use makes a lot of sense, but I don’t really get their tool search approach.

We originally had RAG as a form of search to discover potentially relevant information for the context. Then with MCP we moved away from that and instead dumped all the tool descriptions into the context and let the LLM decide, and it turned out this was way better and more accurate.

Now it seems like the basic MCP approach leads to the LLM context running out of memory due to being flooded with too many tool descriptions. And so now we are back to calling search (not RAG but something else) to determine what’s potentially relevant.

Seems like we traded scalability for accuracy, then accuracy for scalability… but I guess maybe we’ve come out on top because whatever they are using for tool search is better than RAG?

Re: Claude Advanced Tool Use

#56

Post by fofoz »

It’s quite obvious that at some point the entire web will become a collection of billions of tools; Google will index them all, and Gemini will dynamically select them to perform actions in the world for you. Honestly, I expected this with Gemini 3

Re: Claude Advanced Tool Use

#57

Post by awesome_dude »

kspacewalk2 wrote: post #53
awesome_dude wrote: post #50

Earlier quoted context omitted.

Without wishing to take part in a pile on - I am wondering why you're using graphql if you are kneecapping it and restricting it to set queries.

Probably for one of the reasons graphql was created in the first place - accomplish a set of fairly complex operations using one rather than a multitude of API calls. The set can be "everything" or it can be "this well-defined subset".

You could be right, but that's really just "Our API makes multiple calls to itself in the background"

I could be wrong but I thought GraphQL's point of difference from a blind proxy was that it was flexible.

Re: Claude Advanced Tool Use

#59

Post by wrs »

awesome_dude wrote: post #50
wrs wrote: post #45

Earlier quoted context omitted.

It doesn’t actually require that second part. Every time I’ve used it in a production system, we had an approved list of query shapes that were accepted. If the client wanted to use a new kind of query, it was performance tested and sometimes needed to be optimized before approval for use. If you open it up for any possible query, then give that to uncontrolled clients, it’s a recipe for disaster.

Without wishing to take part in a pile on - I am wondering why you're using graphql if you are kneecapping it and restricting it to set queries.

Because it solves all sorts of other problems, like having a well-defined way to specify the schema of queries and results, and lots of tools built around that.

I would be surprised to see many (or any) GQL endpoints in systems with significant complexity and scale that allow completely arbitrary requests.

Re: Claude Advanced Tool Use

#60

Post by menix »

rfw300 wrote: post #15

I am extremely excited to use programmatic tool use. This has, to date, been the most frustrating aspect of MCP-style tools for me: if some analysis requires the LLM to first fetch data and then write code to analyze it, the LLM is forced to manually copy a representation of the data into its interpreter. Programmatic tool use feels like the way it always should have worked, and where agents seem to be going more bro…

smolagents by Hugging Face tackles your issues with MCP tools. They added support for the output schema and structured output provided by the latest MCP spec. This way print and inspect is no longer necessary. https://huggingface.co/blog/llchahn/ai-agents-output-schema
Post reply on HN