"Token anxiety", a slot machine by any other name • Hacker News Board

Re: "Token anxiety", a slot machine by any other name

#151

Post by HolyLampshade » Tue, Feb 17, 2026, 1:39 PM UTC

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand.

When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because I'm in an industry with limited externally available examples to build am model off of (though all of the specifications are public, I've yet to see an agent build an appropriate implementation).

So it's much more transactional...I ask, it does something (usually within seconds), I correct, it iterates again...

What sort of tasks are people putting these agents to? How are people running 'multiple' of these agents? What am I missing here?

Re: "Token anxiety", a slot machine by any other name

#152

Post by timcobb » Tue, Feb 17, 2026, 1:40 PM UTC

ctoth wrote: post #11

The gambling analogy completely falls apart on inspection. Slot machines have variable reward schedules by design — every element is optimized to maximize time on device. Social media optimizes for engagement, and compulsive behavior is the predictable output. The optimization target produces the addiction. What's Anthropic's optimization target??? Getting you the right answer as fast as possible! The variability in…

> The gambling analogy completely falls apart on inspection.

yeah I think the bluesky embed is much more along the lines of what I'm experiencing than the OP itself.

Re: "Token anxiety", a slot machine by any other name

#153

Post by mikrotikker » Tue, Feb 17, 2026, 1:45 PM UTC

HolyLampshade wrote: post #151

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand. When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because…

I wrote a program to classify thousands of images but that was using a model running on my gaming PC. Took about 3 days to classify them all. Only cost me the power right?

Re: "Token anxiety", a slot machine by any other name

#154

Post by flerchin » Tue, Feb 17, 2026, 1:46 PM UTC

HolyLampshade wrote: post #151

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand. When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because…

This is my experience of it too. Perhaps if it was chunking through a large task like upgrading all of our repos to the latest engine supported by our cloud provider, I could leave it overnight. Even then it would just result in a large daylight backlog of "not quite right" to review and redo.

Re: "Token anxiety", a slot machine by any other name

#155

Post by philipwhiuk » Tue, Feb 17, 2026, 1:55 PM UTC

tokioyoyo wrote: post #92

crystal_revenge wrote: post #82

Earlier quoted context omitted.

> What's Anthropic's optimization target??? Getting you the right answer as fast as possible! What makes you believe this? The current trend in all major providers seem to be: get you to spin up as many agents as possible so that you can get billed more and their number of requests goes up. > Slot machines have variable reward schedules by design LLMs by all major providers are optimized used RLHF where they are opti…

> What makes you believe this? Simply, cut-throat competition. Given multiple nations are funding different AI-labs, quality of output and speed are one of the most important things.

Dating apps also have cut-throat competition and none of them are optimised for minimising the time you spend on the app.

Re: "Token anxiety", a slot machine by any other name

#156

Post by jplusequalt » Tue, Feb 17, 2026, 1:56 PM UTC

ctoth wrote: post #11

The gambling analogy completely falls apart on inspection. Slot machines have variable reward schedules by design — every element is optimized to maximize time on device. Social media optimizes for engagement, and compulsive behavior is the predictable output. The optimization target produces the addiction. What's Anthropic's optimization target??? Getting you the right answer as fast as possible! The variability in…

>The pathologizing of "person who likes making things chooses making things over Netflix" requires you to treat passive consumption as the healthy baseline, which is obviously a claim nobody in this conversation is bothering to defend

I think their greater argument was to highlight how agentic coding is eroding work life balance, and that companies are beginning to make that the norm.

Re: "Token anxiety", a slot machine by any other name

#157

Post by philipwhiuk » Tue, Feb 17, 2026, 1:56 PM UTC

mikkupikku wrote: post #129

scuff3d wrote: post #74

Earlier quoted context omitted.

The Max plan has usage limits, and you can buy more... Which is exactly what I'm talking about... And the incentive is even strong for the lower tiers. They want answers to be just good enough to keep you using it, but bad enough that you're pushed towards buying the higher tier.

Have you actually used a max plan? You have to try really damn hard to get close to the max plan usage. I don't think that's something that realistically happens by accident, you have to be deliberately spawning a huge number of subagents or something.

Isn't this why OpenAI just hired the OpenClawd guy? To encourage people to build more agents?

Re: "Token anxiety", a slot machine by any other name

#158

Post by YetAnotherNick » Tue, Feb 17, 2026, 2:04 PM UTC

HolyLampshade wrote: post #151

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand. When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because…

There has only been one instance of coding where I let the agent run for like 7 hours. To generate playwright test. Once the scaffolding is done, it is just matter of writing test for each of the component. But yeah even for that I didn't just fire and forget.

Re: "Token anxiety", a slot machine by any other name

#159

Post by jascha_eng » Tue, Feb 17, 2026, 2:05 PM UTC

HolyLampshade wrote: post #151

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand. When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because…

My impression so far is that the parallel agent story is a fabrication of "ai influencers" and the labs themselves.

I might run 3-4 claude sessions because that's the only way to have "multiple chats" to e.g. ask unrelated things. Occasionally a task takes long enough to keep multiple sessions busy, but that's rather rare and if it happens its because the agent runs a long running task like the whole test suite.

The story of running multiple agents to build full features in parallel... doesn't really add up in my experience. It kinda works for a bit if you have a green field project where the complexity is still extremely low.

However once you have a feature interaction matrix that is larger than say 3x3 you have to hand hold the system to not make stupid assumptions. Or you prompt very precisely but this also takes time and prevents you from ever running into the parallel situation.

The feature interaction matrix size is my current proxy "pseudo-metric" for when agentic coding might work well and at which abstraction level.

Re: "Token anxiety", a slot machine by any other name

#160

Post by wiseowise » Tue, Feb 17, 2026, 2:11 PM UTC

HolyLampshade wrote: post #151

I know I'm running a bit late to the party here, but maybe someone can provide some color that I (on the slightly older end of the spectrum when it comes to this) don't fully understand. When people talk about leaving their agents to run overnight, what are those agents actually doing? The limited utility I've had using agent-supported software development requires a significant amount of hand holding, maybe because…

> what are those agents actually doing

Generate material for yet another retarded twitter hype post.