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

You should write an agent

fly.io

Post reply on HN
Print view View original

311–320 of 409 posts

Re: You should write an agent

#311

Post by philipwhiuk »

fluidcruft wrote: post #119
GoatInGrey wrote: post #108

Earlier quoted context omitted.

So AI companies are profitable when you ignore some of the things they have to spend money on to operate? Snark aside, inference is still being done at a loss. Anthropic, the most profitable AI vendor, is operating at a roughly -140% margin. xAI is the worst at somewhere around -3,600% margin.

If they are not operating inference at a loss and current models remain useful (why would they regress?), they could just stop developing the next model.

At minimum they have to incorporate new data every month or the models will fail to know how many Shrek movies there are and become increasingly wrong in a world that isn't static.

Re: You should write an agent

#312

Post by itsmemattchung »

Zak wrote: post #78

> You only think you understand how a bicycle works, until you learn to ride one. I bet a majority of people who can ride a bicycle don't know how they steer, and would describe the physical movements they use to initiate and terminate a turn inaccurately. https://en.wikipedia.org/wiki/Countersteering

Reminds me of this YouTube video (below) on how difficult it is (nearly impossible) to re-learn how to ride a bicycle when you have the handles are reversed (i.e. pulling left handle bar towards you, the wheel goes to the right)

https://www.youtube.com/watch?v=MFzDaBzBlL0

Re: You should write an agent

#313

Post by andy99 »

singularity2001 wrote: post #246
dave1010uk wrote: post #80

Two years ago I wrote an agent in 25 lines of PHP [0]. It was surprisingly effective, even back then before tool calling was a thing and you had to coax the LLM into returning structured output. I think it even worked with GPT-3.5 for trivial things. In my mind LLMs are just UNIX strong manipulation tools like `sed` or `awk`: you give them an input and command and they give you an output. This is especially true if y…

what's the point of specialized agents when you just have one universal agent that can do anything e.g. Claude

LLMs are good at fuzzy pattern matching and data manipulation. The upstream comment comparing to awk is very apt. Instead of having to write a regex to match some condition you instruct an LLM and get more flexibility. This includes deciding what the next action to take is in the agent loop.

But there is no reason (and lots of downside) to leave anything to the LLM that’s not “fuzzy” and you could just write deterministically, thus the agent model.

Re: You should write an agent

#314

Post by vidarh »

simplesagar wrote: post #61
vidarh wrote: post #37

Earlier quoted context omitted.

I'd second the article on this, but also add to it that the biggest reason MCP servers don't really matter much any more is that the models are so capable of working with APIs , that most of the time you can just point them at an API and give them a spec instead. And the times that doesn't work, just give them a CLI tool with a good --help option . Now you have a CLI tool you can use yourself, and the agent has a too…

I feel the CLI vs MCP debate is an apples to oranges framing. When you're using claude you can watch it using CLI's, running brew, mise, lots of jq but what about when you've built an agent that needs to work through a complicated API? You don't want to make 5 CRUD calls to get the right answer. A curated MCP tool ensures it can determinism where it matters most.. when interacting with customer data

Even in the case where you need to group steps together in a deterministic manner, you don't need an MCP server for that. You just need to bundle those steps into a CLI or API endpoint.

That was my point. Going the extra step and wrapping it in an MCP provides minimal advantage vs. just writing a SKILL.md for a CLI or API endpoint.

Re: You should write an agent

#315

Post by lelanthran »

simonw wrote: post #137
hoppp wrote: post #93

I should? what problems can I solve, that can be only done with an agent? As long as every AI provider is operating at a loss starting a sustainably monetizable project doesn't feel that realistic.

> what problems can I solve, that can be only done with an agent? The problem that you might not intuitively understand how agents work and what they are and aren't capable of - at least not as well as you would understand it if you spent half an hour building one for yourself.

>> what problems can I solve, that can be only done with an agent?

> The problem that you might not intuitively understand how agents work and what they are and aren't capable of

I don't necessarily agree with the GP here, but I also disagree with this sentiment: I don't need to go through the experience of building a piece of software to understand what the capabilities of that class of software is.

Fair enough, with most other things (software or otherwise), they're either deterministic or predictably probabilistic, so simply using it or even just reading how it works is sufficient for me to understand what the capabilities are.

With LLMs, the lack of determinism coupled with completely opaque inner-workings is a problem when trying to form an intuition, but that problem is not solved by building an agent.

Re: You should write an agent

#316

Post by fluidcruft »

philipwhiuk wrote: post #311
fluidcruft wrote: post #119

Earlier quoted context omitted.

If they are not operating inference at a loss and current models remain useful (why would they regress?), they could just stop developing the next model.

At minimum they have to incorporate new data every month or the models will fail to know how many Shrek movies there are and become increasingly wrong in a world that isn't static.

That sort of thing isn't necessary for all use cases. But if you're relying on the system to encode wikipedia or the zeitgeist then sure.

Re: You should write an agent

#317

Post by singularity2001 »

fennecbutt wrote: post #310
ljm wrote: post #294

Earlier quoted context omitted.

Composing multiple smaller agents allows you to build more complex pipelines, which is a lot easier than getting a single monolithic agent to switch between contexts for different tasks. I also get some insight into how the agent performs (e.g via langfuse) because it’s less of a black box. To use an example: I could write an elaborate prompt to fetch requirements, browse a website, generate E2E test cases, and compi…

Plus I'd say that the smaller context or more specific context is the important thing there. Even the biggest models seem to have attention problems if you've got a huge context. Even though they support these long contexts it's kinda like a puppy distracted by a dozen toys around the room rather than a human going through a checklist of things. So I try to give the puppy just one toy at a time.

OK so instead of my current approach of doing a single task at a time (and forgetting to clear the context;) this will make it more feasible to run longer and more complex tasks I think I get it.

Re: You should write an agent

#318

Post by monomers »

baq wrote: post #253
singularity2001 wrote: post #246

Earlier quoted context omitted.

what's the point of specialized agents when you just have one universal agent that can do anything e.g. Claude

If you can get a specialized agent to work in its domain at 10% parameters of a foundation model, you can feasibly run locally, which opens up e.g. offline use cases. Personally I’d absolutely buy an LLM in a box which I could connect to my home assistant via usb.

What use cases do you imagine for LLMs in home automation?

I have HA and a mini PC capable of running decently sized LLMs but all my home automation is super deterministic (e.g. close window covers 30 minutes after sunset, turn X light on if Y condition, etc.).

Re: You should write an agent

#319

Post by 8cvor6j844qw_d6 »

simonw wrote: post #238
sumedh wrote: post #236

Earlier quoted context omitted.

Dont you need to setup Playwright MCP first?

No. I don't use Playwright MCP at all - if the coding agent can run Python code it can use the Playwright Python library directly, if Node.js it can use the Playwright Node library.

Oh wow Simon Willison, I've read some of your submissions on HN and its very informative.

Thank you very much for the info. I think I'll have a fun weekend trying out agent-stuff with this [1].

[1]: https://vercel.com/guides/how-to-build-ai-agents-with-vercel...

Re: You should write an agent

#320

Post by pjmlp »

dave1010uk wrote: post #80

Two years ago I wrote an agent in 25 lines of PHP [0]. It was surprisingly effective, even back then before tool calling was a thing and you had to coax the LLM into returning structured output. I think it even worked with GPT-3.5 for trivial things. In my mind LLMs are just UNIX strong manipulation tools like `sed` or `awk`: you give them an input and command and they give you an output. This is especially true if y…

And that is how we end up with iPaaS products powered by agentic runtimes, slowly dragging us away from programming language wars.

Only a selected few get to argue about what is the best programming language for XYZ.

Post reply on HN