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

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

jkap.io

Post reply on HN
Print view View original

181–190 of 249 posts

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

#181

Post by randusername »

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…

Disagree. Unreliability is intractable because of the human, not the tool.

Even a perfect LLM will not be able to produce perfect outputs because humans will never put in all the context necessary to zero-shot any non-trivial query. LLMs can't read your mind and will always make distasteful assumptions unless driven by users without any unique preferences or a lot of time on their hands to ruminate on exactly how they want something done.

I think it will always be mostly boring back-and-forth until the jackpot comes. Maybe future generations will align their preferences with the default LLM output instead of human preferences in that domain, though.

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

#182

Post by zvqcMMV6Zcr »

Please tell me this is some kind of satire because people checking on agents makes as much sense as people waking up early only to checking progress on Gentoo rebuilding itself from sources. Which definitely happened but as a niche not something common enough to observe.

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

#183

Post by candiddevmike »

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…

Maybe it's the programmer equivalent of rolling coal.

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

#184

Post by HolyLampshade »

flerchin wrote: post #154
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.

I think that's the issue I have with using these tools so far (definitely professionally, but even in pet projects for embedded systems). The mental load of having to go back through and make sure all of the lines of code do what the agent claims they do, even with tests, is significantly more than it would take to learn the implementation myself.

I can see the utility in creating very simple web-based tools where there's a monstrous wealth of public resources to build a model off of, but even the most recent models provided by Anthro, OpenAI, or MSFT seem prone to not quite perfection. And every time I find an error I'm left wondering what other bugs I'm not catching.

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

#185

Post by otikik »

ctoth wrote: post #58
scuff3d wrote: post #52

Earlier quoted context omitted.

Right. A platform who makes money the more you have to use it is definitely optimizing to get you the right answer in as few tokens as possible. There is absolutely no incentive to do that, for any of these companies. The incentive is to make the model just bad enough you keep coming back, but not so bad you go to a competitor. We've already seen this play out. We know Google made their search results worse to drive…

Please go read how the Anthropic max plan works. IF I USE LESS TOKENS, ANTHROPIC GETS MORE MONEY! You are blindly pattern matching to "corporation bad!" without actually considering the underlying structure of the situation. I believe there's a phrase for this to do with probabilistic avians?

We are on the pre-enshittification phase.

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

#186

Post by nerdsniper »

jascha_eng wrote: post #159
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…

This is exactly my experience as well. The feature interaction matrix is growing as models get better, and I tend to build "prompt library components" for each project which saves time on "you prompt very precisely but this also takes time".

But so far that doesn't change the reality - I can't find any opportunities to let an agent run for more than 30 minutes at best, and parallel agents just seem to confuse each other.

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

#187

Post by LeonidBugaev »

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 had a few useful examples of this. In order to make it work you need to define your quality gates, and rather complex spec. I personally use https://github.com/probelabs/visor for creating the gates. It can be a code-review gate, or how well implementation align with the spec and etc. And basically it makes agent loop until it pass it. One of the tips, especially when using Claude Code, is explictly ask to create a "tasks", and also use subagents. For example I want to validate and re-structure all my documentation - I would ask it to create a task to research state of my docs, then after create a task per specific detail, then create a task to re-validate quality after it has finished task. You can also play around with the gates with a more simple tooling, for example https://probelabs.com/vow/

Hope it helps!

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

#188

Post by QuadrupleA »

jonahrd wrote: post #167
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 might be able to shine a little light on this. I came from embedded, where I wasn't able to use agents very effectively for anything other than quick round trip iterative stuff. They were still really useful, but I definitely could never envision just letting an agent run unattended. But I recently switched domains into vaguely "fullstack web" using very popular frameworks. If I spend a good portion of my day going…

The amount of boilerplate people talk about seems like the fault of these big modern frameworks honestly. A good system design shouldn't HAVE so much boilerplate. Think people would be better off simplifying and eliminating it deterministically before reaching for the LLM slot machine.

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

#189

Post by piperswe »

wordpad wrote: post #170
forgetfreeman wrote: post #104

Earlier quoted context omitted.

sigh We're doing this lie again? Quality of Outcome is not, has never been, and if the last 40 years are anything to go on will never be a core or even tangential goal. Dudes are trying to make the stock numbers go up and get paid. That's it. That's all it ever is.

You're just being pedantic and cynical. Goal of any business in principle is profit, by your terms all of them are misaligned. Matter of fact is that customers are receiving value and the value has been a good proxy for which company will grow to be successful and which will fail.

I mean, yeah. All businesses are misaligned, unless a fluke aligns the profit motive with the consumers for a brief period.

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

#190

Post by Leynos »

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…

With 5.3 Codex, the execplans skill and a well specified implementation task, you can get a good couple of hours work in a single turn. That's already in the scope of "set it up before bed and review it in the morning".

If you have a loop set up, e.g., using OpenClaw or a Ralph loop, you can stretch that out further.

I would suggest that when you get to that point really, you want some kind of adversarial system set up with code reviews (e.g., provided by CodeRabbit or Sourcery) and automation to feed that back into the coding agent.

Post reply on HN