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

Tools: Code Is All You Need

lucumr.pocoo.org

Post reply on HN
Print view View original

81–90 of 234 posts

Re: Tools: Code Is All You Need

#81

Post by giovannibonetti »

jangxx wrote: post #60
foobarbecue wrote: post #29

Earlier quoted context omitted.

Hype cycle for drones and VR was similar -- at the peak, you have people claiming drones will take over package delivery and everyone will spend their day in VR. Reality is that the applicability is more narrow.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

Drones and VR require significant upfront hardware investment, which curbs adoption. On the other hand, adopting LLM-as-a-service has none of these costs, so no wonder so many companies are getting involved with it so quickly.

Re: Tools: Code Is All You Need

#82

Post by soulofmischief »

foobarbecue wrote: post #29
pclowes wrote: post #5

Directionally I think this is right. Most LLM usage at scale tends to be filling the gaps between two hardened interfaces. The reliability comes not from the LLM inference and generation but the interfaces themselves only allowing certain configuration to work with them. LLM output is often coerced back into something more deterministic such as types, or DB primary keys. The value of the LLM is determined by how well…

Hype cycle for drones and VR was similar -- at the peak, you have people claiming drones will take over package delivery and everyone will spend their day in VR. Reality is that the applicability is more narrow.

That's the claim for AR, not VR, and you're just noticing how research and development cycles play out, you can draw comparisons to literally any technology cycle.

Re: Tools: Code Is All You Need

#83

Post by the_mitsuhiko »

JyB wrote: post #57
the_mitsuhiko wrote: post #50

Earlier quoted context omitted.

> This is solved trivially by having default initial prompts. All majors tools like Claude Code or Gemini CLI have ways to set them up. That only makes it worse. The MCP tools available all add to the initial context. The more tools, the more of the context is populated by MCP tool definitions.

Do you mean that some tools (MCP clients) pass all functions of all configured MCP servers in the initial prompt? If that's the case: I understand the knee-jerk reaction but if it works? Also what theoretically prevents altering the prompt chaining logic in these tools to only expose a condensed list of MCP servers, not their whole capabilities, and only inject details based on LLM outputs? Doesn't seem like an insur…

> Do you mean that some tools (MCP clients) pass all functions of all configured MCP servers in the initial prompt?

Not just some, all. That's just how MCP works.

> If that's the case: I understand the knee-jerk reaction but if it works?

I would not be writing about this if it worked well. The data indicates that it worse significantly worse than not using MCP because of the context rot, and the low too utilization.

Re: Tools: Code Is All You Need

#84

Post by tristanz »

You can combine MCPs within composable LLM generated code if you put in a little work. At Continual (https://continual.ai), we have many workflows that require bulk actions, e.g. iterating over all issues, files, customers, etc. We inject MCP tools into a sandboxed code interpreter and have the agent generate both direct MCP tool calls and composable scripts that leverage MCP tools depending on the task complexity. After a bunch of work it actually works quite well. We are also experimenting with continual learning via a Voyager like approach where the LLM can save tool scripts for future use, allowing lifelong learning for repeated workflows.

Re: Tools: Code Is All You Need

#85

Post by pxc »

jangxx wrote: post #60
foobarbecue wrote: post #29

Earlier quoted context omitted.

Hype cycle for drones and VR was similar -- at the peak, you have people claiming drones will take over package delivery and everyone will spend their day in VR. Reality is that the applicability is more narrow.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

A parallel outcome for LLMs sounds realistic to me.

Re: Tools: Code Is All You Need

#86

Post by wrs »

lsaferite wrote: post #35
gbrindisi wrote: post #7

Earlier quoted context omitted.

wouldn't this defeat the point? Claude Code already has access to the terminal, adding specific instruction in the context is enough

No. You are giving textual instructions to Claude in the hopes that it correctly generates a shell command for you vs giving it a tool definition with a clearly defined schema for parameters and your MCP Server is, presumably, enforcing adherence to those parameters BEFORE it hits your shell. You would be helping Claude in this case as you're giving a clearer set of constraints on operation.

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. And presumably the command is enforcing constraints even better than the MCP server would.

Re: Tools: Code Is All You Need

#87

Post by dist-epoch »

simonw wrote: post #75
dist-epoch wrote: post #49

Earlier quoted context omitted.

I've been using a VM for a sandbox, just to make sure it won't delete my files if it goes insane. With some host data directories mounted read only inside the VM. This creates some friction though. Feels like a tool which runs the AI agent in a VM, but then copies it's output to the host machine after some checks would help, so that it would feel that you are running it natively on the host.

Have you tried giving the model a fresh checkout in a read-write volume?

Hmm, excellent idea, somehow I assumed that it would be able to do damage in a writable volume, but it wouldn't be able to exit it, it would be self-contained to that directory.

Re: Tools: Code Is All You Need

#88

Post by deadbabe »

jangxx wrote: post #60
foobarbecue wrote: post #29

Earlier quoted context omitted.

Hype cycle for drones and VR was similar -- at the peak, you have people claiming drones will take over package delivery and everyone will spend their day in VR. Reality is that the applicability is more narrow.

I mean both of these things are actually happening (drone deliveries and people spending a lot of time in VR), just at a much much smaller scale than it was hyped up to be.

If it’s not happening at the scale it was pitched, then it’s not happening.

Re: Tools: Code Is All You Need

#89

Post by deadbabe »

whiplash451 wrote: post #32
pclowes wrote: post #5

Directionally I think this is right. Most LLM usage at scale tends to be filling the gaps between two hardened interfaces. The reliability comes not from the LLM inference and generation but the interfaces themselves only allowing certain configuration to work with them. LLM output is often coerced back into something more deterministic such as types, or DB primary keys. The value of the LLM is determined by how well…

Interesting take but too bearish on LLMs in my opinion. LLMs have already found large-scale usage (deep research, translation) which makes them more ubiquitous today than 3D printers ever will or could have been.

large scale usage in niche domains is still small scale overall.

Re: Tools: Code Is All You Need

#90

Post by wrs »

MCP is literally the same as giving an LLM a set of man page summaries and a very limited shell over HTTP. It’s just in a different syntax (JSON instead of man macros and CLI args).

It would be better for MCP to deliver function definitions and let the LLM write little scripts in a simple language.

Post reply on HN