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

The current hype around autonomous agents, and what actually works in production

utkarshkanwat.com

Post reply on HN
Print view View original

221–230 of 268 posts

Re: The current hype around autonomous agents, and what actually works in production

#221

Post by nsonha »

throwehshdhdy wrote: post #204
Arn_Thor wrote: post #200

I spoke with an Amazon AI production engineer who’s talking with prospective clients about implementing AI in our business. When a colleague asked about using generative AI in customer facing chats the engineer said he knows of zero companies who don’t have a human in the loop. All the automatic replies are non-generative “old” tech. Gen AI is just not reliable enough for anyone to stake their reputation on it.

Plenty of tech companies have started using gen AI for live chat support. Off the top of head I know off sonder.com and wealthsimple.com. If the LLM can’t answer a query it usually forwards the chat to a human support agent.

Of course it can but I think the issue is that people may try to jailbreak it or do something funny to get a weird response, then post of x.com against the company. There must be techniques to turn LLMs into a FAQ forwarding bot, but then what's the point of having a LLM

Re: The current hype around autonomous agents, and what actually works in production

#222

Post by andrekandre »

dmezzetti wrote: post #6

It's clear that what we currently call AI is best suited for augmentation not automation. There are a lot of productivity gains available if you're willing to accept that.

  > AI is best suited for augmentation not automation.
i agree with this sentiment, but with the caveat of "when its not lying to you".

the most frustrating part of these interactive ai assistants is when it sends me down a rabbit hole of an api that doesn't exist (but looks almost right)

Re: The current hype around autonomous agents, and what actually works in production

#223

Post by fleebee »

stavros wrote: post #178
fleebee wrote: post #77

Earlier quoted context omitted.

The graphs don't line up. I'm inclined to believe they were hallucinated by an LLM and the author either didn't check them or didn't care. Judging by the other comments this is clearly low-effort AI slop. > LLMs have certainly damaged trust in general internet reading now, that's for sure. I hate that this is what we have to deal with now.

I don't know why you do. I found the article interesting, derived value from it. I don't care if it's an LLM or a human that gave me the value. I don't see why it should matter.

It matters to me for so many reasons that I can't go over them all here. Maybe we have different priorities, and that's fine.

One reason why LLM generated text bothers me is because there's no conscious, coherent mind behind it. There's no communicative intent because language models are inherently incapable of it. When I read a blog post, I subconsciously create a mental model of the author, deduce what kind of common ground we might have and use this understanding to interpret the text. When I learn that an LLM generated a text I've read, that mental model shatters and I feel like I was lied to. It was just a machine pretending to be a human, and my time and attention could've been used to read something written by a living being.

I read blogs to learn about the thoughts of other humans. If I wanted to know what an LLM thought about the state of vibe coding, I could just ask one at any time.

Re: The current hype around autonomous agents, and what actually works in production

#224

Post by a_bonobo »

sarchertech wrote: post #106
Filligree wrote: post #91

Earlier quoted context omitted.

The standard way to use Claude Code is with a constant-cost subscription; one of their standard website accounts. It’s rate-limited but still generous. You can also use API tokens, yes, but that’s 5-10x more expensive. So I wouldn’t.

If API tokens are 10x more expensive doesn’t that imply that the constant-cost subscription is massively subsidized?

yes, definitely. I've seen comments from people burning through $100s of tokens per day for a $200 per month subscription. Anthropic has just been cracking down and restricted token limits for restrictions, expect more to come, it's just not sustainable

https://techcrunch.com/2025/07/17/anthropic-tightens-usage-l...

Re: The current hype around autonomous agents, and what actually works in production

#225

Post by gf000 »

antisthenes wrote: post #195
alpha_squared wrote: post #136

One thing I'll add that isn't touched on here is about context windows. While not "infinite", humans have a very large context window for problems they're specialized in solving. Models can often overcome their context window limitations by having larger and more diverse training sets, but that still isn't really a solution to context windows. Yes, I get the context window increases over time and that for many purpos…

> humans have a very large context window for problems they're specialized in solving Do they? I certainly don't. I don't know if it's my memory deficiency, but I frequently hit my "context window" when solving problems of sufficient complexity. Can you provide some examples of problems where humans have such large context windows?

It's a very large context window, but it is compressed down a lot. I don't know every line of insert your PL of choice's standard library, but I do know a lot of it with many different excerpts from the documentation, relevant experiences where I used this over that, or edge cases/bugs that one might fall into. Add to it all the domain knowledge for the given project, with explicit knowledge of how the clients will use the product, etc, but even stuff like what might your colleague react to to this approach vs another.

And all this can be novelly combined and reasoned with to come up with new stuff to put into the "context window", and it can be dynamically extended at any point (e.g. you recall something similar during a thought train and "bring it into context").

And all this was only the current task-specific window, which lives inside the sum total of your human experience window.

Re: The current hype around autonomous agents, and what actually works in production

#226

Post by a_bonobo »

>Enterprise systems aren't clean APIs waiting for AI agents to orchestrate them. They're legacy systems with quirks, partial failure modes, authentication flows that change without notice, rate limits that vary by time of day, and compliance requirements that don't fit neatly into prompt templates.

Perhaps that's why MCP as a protocol is so interesting to people - MCP servers are a chance at a 'blank slate' in front of the enterprise system. You pull out only the parts you're interested in, you get to define clear boundaries when you build the MCP server, the LLM sees only what you want it to see and you hide the messiness of the enterprise system.

Re: The current hype around autonomous agents, and what actually works in production

#227

Post by sarchertech »

stavros wrote: post #182
sarchertech wrote: post #109

Earlier quoted context omitted.

That works because each plane is (nearly) exactly the same as the one before it and we have exact specifications for the plane. You can do maintenance, inspections, and replacement because of those specifications. In software the equivalent of blueprints is code. The room for variation outside software “specifications” is infinite. Human reliability when comes to assembling planes is also much higher than 99%, and LL…

If you think human reliability when writing code is more than 99%, have I got news for you!

If you’re going by bugs per lines of code, I’m far higher than 99% reliable.

Re: The current hype around autonomous agents, and what actually works in production

#228

Post by eska »

a_bonobo wrote: post #226

>Enterprise systems aren't clean APIs waiting for AI agents to orchestrate them. They're legacy systems with quirks, partial failure modes, authentication flows that change without notice, rate limits that vary by time of day, and compliance requirements that don't fit neatly into prompt templates. Perhaps that's why MCP as a protocol is so interesting to people - MCP servers are a chance at a 'blank slate' in front…

It’s on the wrong layer for that. MCP is akin to putting GraphQL over an old and crufty SOAP interface. There’s some “intelligence” in the GraphQL layer, but it doesn’t fix flaws in the lower layer such as side effects that shouldn’t be there.

Re: The current hype around autonomous agents, and what actually works in production

#229

Post by eska »

ankit219 wrote: post #171

These are all solvable problems. The issue is given the race to get to a certain ARR quickly, many startups end up not focusing on these. There is some truth to AI agents being not as useful as their promise, but the problems mentioned are engineering problems, and once we start seeing them with a different lens, they would start working. (This is not to say I believe orchestration or multi step agents are a way to g…

That’s a common fallacy. I suggest you make a plot of failure rate vs amount of components that can fail, any one of them failing leading to a total failure. You’ll be shocked by how quickly you get terrible numbers.

Re: The current hype around autonomous agents, and what actually works in production

#230

Post by _heimdall »

bakugo wrote: post #100
_heimdall wrote: post #28

Earlier quoted context omitted.

It that just avoids having to send the full context for follow-up requests, right? My understanding is that caching helps to keep the context around but can't avoid the need to process that context over and over during inference.

The initial context processing is also cached, which is why there's a significant discount on the input token cost.

What exactly is cached though? Each loop of token inference is effectively a recursive loop that takes in all context plus all previously inferred tokens, right? Are they somehow caching the previously inferred state and able to use that more efficiently than if they just cache the context then run it all through inference again?
Post reply on HN