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

Claude Fable is relentlessly proactive

simonwillison.net

Post reply on HN
Print view View original

491–500 of 748 posts

Re: Claude Fable is relentlessly proactive

#491

Post by jcfrei »

bsza wrote: post #280
exitb wrote: post #233

Earlier quoted context omitted.

You’ve picked an interesting example, as driving a car, even with all safety precautions, is pretty much the most dangerous activity we do on a daily basis. Yet somehow we decide that the benefits outweigh the risks.

It's a completely different story. For cars, it happened because of relentless pressure from the auto lobby. It took years of propaganda from oil companies, car makers etc. to make us think the road is for cars [1]. We demolished and rebuilt entire cities to accommodate cars, partly because they gutted the public transport sector [2]. This made our infrastructure so hostile to our own bodies that we have no choice bu…

Whether public or individual transportation makes more sense really depends on a country’s geography and people’s housing preferences. Public transportation is not always the best option.

Re: Claude Fable is relentlessly proactive

#492

Post by lolinder »

AmbroseBierce wrote: post #452
simonw wrote: post #399

Earlier quoted context omitted.

Here's a handy calculator you can use to estimate how much CO2 and water I wasted with my coding agent session: https://www.andymasley.com/visuals/ai-prompt-footprint/

This very obtusely ommits the demand for new data centers and related infrastructure that using AI creates, the going "vegan for a year" option assumes less cows being born but somehow the "don't use AI" doesn't assume that the data center wasn't build in the first place.

The discrete number of cows being born is theoretically fine-grained enough to actually respond to 2–3 vegans yielding one fewer cow. It's unlikely on a one-year time scale, but one cow only goes so far.

Even a thousand AI objectors aren't going to limit the demand for a data center, in no small part because these investments are only partially driven by current demand and are significantly driven by expectation of future demand. And they're really not going to lead to smaller data centers either because if you're building a data center in the first place you're going to spec it out for future demand.

Regardless, I think in both cases it's important to be realistic about the actual impact that one person has. If that number is disappointingly small, that serves as signal that your conscientious objection isn't making the industry you're objecting to as uncomfortable as you would like to think. It may still be worth objecting for your own sense of self, or maybe it serves as an invitation to evangelize your position more, but either way there's not much value to measuring things in a way that gives you an illusion of greater impact than you actually have.

Re: Claude Fable is relentlessly proactive

#493

Post by _345 »

rfw300 wrote: post #226
_345 wrote: post #165

Earlier quoted context omitted.

way worse things can happen than your machine being bricked, if a malicious actor can weaponize an agent to do their bidding

> if a malicious actor can weaponize an agent to do their bidding In my experience, human employees are much more vulnerable to this particular weakness than frontier agents (i.e. phishing attacks).

I'm not letting Jenna from HR log into my personal machine with access to all of my lifelong data though. I do let my claude bypass permissions though

Re: Claude Fable is relentlessly proactive

#494

Post by geysersam »

bananaquant wrote: post #338

This to me reads like a poignant commentary on the catastrophic loss of human agency, with the actual commit being highly revealing [0]. Author wants to hide a horizontal scrollbar. Any junior frontend dev worth their salt will be asking right away "where do I stick `overflow-x: hidden;`?" A complete solution will then require hitting "Inspect element" in the browser to find the CSS class and running (rip)grep to fin…

This is the worst thing about current AI agents. They never ask questions. The prompt has to be pixel perfect and unambiguous or they'll happily run away doing something ridiculous.

Re: Claude Fable is relentlessly proactive

#495

Post by brainless »

This is good and terrible. The extra effort a model has taken is good but the way to do it is terrible. Tasks that can use a lot of deterministic paths and some creative (generative AI) paths are being turned into tokemaxxing strategies.

Browser automation, code comprehension, git management, code change, running commands - everything has simpler tooling that we could have built instead of a model first approach. A deterministic loop with thousands of catches and effective use of generative AI would also look "proactive". Instead we let the model run the tools, where tools have no context themselves.

That is why companies are creating bigger models and thinner deterministic agents to create awe and earn $ when we could go the other way and make much of these possible on local inference even.

I believe we can build a "proactive" but much, much more deterministic system with smaller models. I hope I am not the only one chasing this, here is my approach: https://github.com/brainless/nocodo

Re: Claude Fable is relentlessly proactive

#496

Post by deaux »

beernet wrote: post #371
oulipo2 wrote: post #366

Earlier quoted context omitted.

[flagged]

[flagged]

As someone who actually gives a shit about the environment and global warming and has been putting this into practice for more than a decade through daily personal sacrifices: no, I downvote it because if you properly look into it, AI is just completely insignificant compared to cars, air travel, clothing, food, needless junk and so on that it's a joke. It's always brought up by people who never cared, but now pretend to do so because they hate LLMs for other reasons. The irony is that some of those are actually _good_ reasons but they're too cowardly to admit them. There's nothing unmanly about admitting you're afraid of AI taking your job, becoming more intelligent, and ending up in a dystopia.

Go run the numbers and compare them vs. what it takes to produce a single hamburger or hoodie. Anyone who actually cares has already done this and drawn this conclusion.

Re: Claude Fable is relentlessly proactive

#497

Post by nevertoolate »

Cadwhisker wrote: post #100

My personal experience of Fable 5 doing its own thing has been very positive. I was trying to find the root cause of a crash in a Python module which left no errors in the log or console. Fable wrote a test harness that simulated clicks in the UI, then bisected my code until it found the point where it started crashing. It exaggerated the cause of the crash, then ran a series of bash one-liners to make Python virtual…

> I was trying to find the root cause of a crash in a Python module which left no errors in the log or console. Fable wrote a test harness that simulated clicks in the UI, then bisected my code until it found the point where it started crashing

Does this need an agent though is my question? Maybe generating a test case and a loop doing git bisect but why on earth would we want to run it through the internet and gpus and whatnot when it can be run on a single core celeron.

Re: Claude Fable is relentlessly proactive

#498

Post by joseda-hg »

tabs_or_spaces wrote: post #348

How can a LLM be assigned an emotion as being "proactive". This is highly misleading to anyone that scans just the headlines. What actually happened is that the user started a prompt, and Claude took $12 worth of tokens to resolve the issue. How it did so was basically looping until it got to the answer How is this proactive? It's literally being token greedy and maximising revenue for the LLM owner. People really ne…

Compared to other models that halt the loop on intermediate steps, or to ask further clarification, even if it's not the human equivalent of proactive, you see the similarity, right?

Re: Claude Fable is relentlessly proactive

#499

Post by andy_ppp »

bananaquant wrote: post #338

This to me reads like a poignant commentary on the catastrophic loss of human agency, with the actual commit being highly revealing [0]. Author wants to hide a horizontal scrollbar. Any junior frontend dev worth their salt will be asking right away "where do I stick `overflow-x: hidden;`?" A complete solution will then require hitting "Inspect element" in the browser to find the CSS class and running (rip)grep to fin…

Yes I agree, the solution committed is horrible, but nobody cares any more. We have entered a very strange parallel universe where because AI can work things out it's easier to take solutions that are sub optimal and just churn out (potentially) buggy features.

Re: Claude Fable is relentlessly proactive

#500

Post by Majromax »

qurren wrote: post #130
satvikpendem wrote: post #118

Earlier quoted context omitted.

You can get 10x shit done without `rm -rf`ing your files. I don't see any correlation to getting things done with having a proper sandbox.

I haven't yet had an agent rm -rf files. I've had one f up an account by placing 2000 limit orders at the wrong price, but that's another story.

> I haven't yet had an agent rm -rf files.

That happened to me once; I was running one of a few free-tier models in a pi-coding-agent session. The bash tool there is stateless and always begins from the launch directory, but the agent assumed state and executed `rm -rf .` intending to remove a build directory. Instead it removed the whole project tree, including session logs and notes.

This was mostly a matter of amusement for me since I was running the agent inside a bubblewrap sandbox for that very reason, and the project itself was not very important.

Post reply on HN