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

If Claude Fable stops helping you, you'll never know

jonready.com

Post reply on HN
Print view View original

421–430 of 534 posts

Re: If Claude Fable stops helping you, you'll never know

#421

Post by soco »

vidarh wrote: post #395
windowshopping wrote: post #311

Earlier quoted context omitted.

> I think we agree? That is such a crazy way to start a response to someone trying to argue with you. I should try this. That's amazing. I know you didn't mean it as a trick, at least I'm pretty sure you meant it sincerely, but I'm just struck by the power of it to defuse and redirect the conversation. And this was a very low-grade example, but I could imagine this being useful in much more heated contexts.

I think in general stripping away the parts you agree with from the argument works great, because it strips away a whole lot of potential for ending up indirectly arguing over things that aren't in contention, and it often also defuses the rest when it turns out the core of the argument perhaps is much smaller than people are willing to get invested in.

How do you do that without sounding negative? Because by doing that there's the risk of the general impression "we didn't agree", as you basically focused on the disagreements.

Re: If Claude Fable stops helping you, you'll never know

#423

Post by rootlocus »

port11 wrote: post #380
hagbarth wrote: post #368

Earlier quoted context omitted.

The alternative is to be explicit when you nerf, so users know what they are working with.

I guess people would just game the system and find ways around these guardrails.

They have enough info on you and your sessions to eventually catch you, label you as bad faith actor and ban you automatically. I don't think many would risk it.

Re: If Claude Fable stops helping you, you'll never know

#424

Post by dudisubekti »

Paradigma11 wrote: post #364
dudisubekti wrote: post #279

Earlier quoted context omitted.

But harness is relatively easy to code yourself? They're just system prompt composer, with some tool functions that the LLM can invoke. I've vibe coded my own in just one day.

But is there anything preventing them from putting their own proprietary wolfram alpha/prolog/super duper expert system in there?

I guess... but I think, at its core, a good coding harness usually includes:

- well-crafted system prompt that follows best practices

- good contextual reminder prompts (when an llm got stuck in an infinite loop and times out, forgets how to use tools, or needs recurring best practice reminders, etc)

- well-written ergonomic tools the llm can use (read/write files, read diffs, browse the internet, etc)

I dont think these are anything special. The deepest moat I can think of is, proprietary models can be specifically trained to use their proprietary harnesses, so they are more token-efficient and make less tool call and file editing mistakes.

However in my experience, I'm as comfortable working with my own homemade harness as with Claude Code, so I don't think it's a deep moat...

Re: If Claude Fable stops helping you, you'll never know

#425

Post by jech »

gruez wrote: post #209
HoldOnAMinute wrote: post #167

Earlier quoted context omitted.

Building a virus, on your own network, probably isn't a crime. We already have all kinds of laws to catch and punish people when they cause harm.

>Building a virus, on your own network, probably isn't a crime. There are plenty of legal uses for a fully automatic AR-15 too, yet we still ban it.

> There are plenty of legal uses for a fully automatic AR-15

Such as?

Re: If Claude Fable stops helping you, you'll never know

#426

Post by michaelscott »

JoshTriplett wrote: post #204
nullc wrote: post #188

Earlier quoted context omitted.

> "YOLO" is not a reasonable answer here. Yes it is. (1) Ordinary people were able to do these things pre AI-- with some effort into study for sure. (2) The cat is already out of the bag, open models can already help with these tasks. I know freedom is frightening, but it always has been. It's important to avoid falling into the trap of assuming that everything that existed when you gained awareness was safe and norm…

Kindly drop the condescension. It is, in fact, possible for the world to get more dangerous over time . It is important to avoid falling into the trap of assuming that's inevitable. > Ordinary people were able to do these things pre AI-- with some effort into study for sure. Yes, and the amount of study and knowledge required had a tendency to filter out people with the inclination to do such things. The Venn diagram…

It is not a given that we should allow computers to exist, the risk of harm is too great.

It is not a given that we should allow vehicles to exist, the risk of harm is too great.

It is not a given that we should allow hammers to exist, the risk of harm is too great.

The argument, even if it weren't moot due to the cat already being long out of the bag, is recursive all the way back to the discovery of fire. As a species we already regulate things that can cause harm in ways that are commensurate with the potential for that harm. Some are regulated more, some less, depending on the region. But all these things exist regardless; you have to decide whether you're comfortable with elites and governments being the only people who should have access to this, especially given that they have a history of not keeping your best interests in mind, or whether it should be democratized and available to all (like most other tools in existence)

Re: If Claude Fable stops helping you, you'll never know

#427

Post by Ukv »

testbjjl wrote: post #379
yuppiepuppie wrote: post #366

Earlier quoted context omitted.

What evidence do you have of this?

Have you had an opportunity to read the linked article, or am I missing your counter argument to what the author references from the documentation?

The documentation claims it's new (Fable 5 released yesterday), whereas the comment claims it's been happening for several years.

Re: If Claude Fable stops helping you, you'll never know

#428

Post by jsw97 »

azalemeth wrote: post #382
jsw97 wrote: post #184

Given the high rate of false positives people are reporting for the non-silent cybersecurity, biological, etc., safeguards, there is a strong likelihood that you will encounter silently nerfed behavior even if you are _not_ violating their TOS. Ultimately this will be evident in the way customers / external benchmarkers experience Fable. Hopefully competition will drive future models toward a lower false positive rat…

I'm a medical physicist. I use the word nuclear a lot. Opus is fine (well, 99% of the time - I've certainly hit the CBRN filters a few times and even been invited to email anthropic about the false positives). Fable has literally refused to work on any of my problems (even those about fluid dynamics!) and just tells me that I'm violating anthropic's AUP.

This problem is compounded by the fact that you can be banned (really by any provider) based on an algorithm, and the methods for restoring your account seem like they do not function as well as might be desired. So be careful with your queries, basically, or you might get locked out.

Re: If Claude Fable stops helping you, you'll never know

#429

Post by Meneth »

stratos123 wrote: post #105
somesortofthing wrote: post #29

This is a fun peek into the economic implications of RSI/ASI. Because it's so infinitely valuable that it basically destroys all markets, labs will eventually do stuff like stop releasing models completely and skipping out on contracted commitments because they'll have the power to just drive their competitors out of business before the legal battle gets expensive. Cloud providers - at first smaller ones, then the hy…

I don't think this scenario makes sense. It's one of a class of scenarios I've seen several of, that simultaneously assume: A) ASI is developed and massively overshadows the rest of the world economy B) the world still has rule of law, contracts, business, well-developed finance, etc You can get to a lot of weird conclusions if you assume both A and B, but I think the much more likely scenario is that if A happens, B…

The "everyone dies" scenario is overwhelmingly likely given that no solutions to either inner or outer alignment exist.

[1] https://en.wikipedia.org/wiki/AI_alignment

Re: If Claude Fable stops helping you, you'll never know

#430

Post by jpfromlondon »

jatora wrote: post #264
hedora wrote: post #85

Earlier quoted context omitted.

What moat? There are multiple companies providing pareto-optimal frontier models, and it takes O(10) people to build one of these things. The rest is capital intensive, and the price will approach the cost of production over time. Thinking this is a profitable endeavor is equivalent to claiming coal plants have good margins because boilers are expensive.

Other models arent even close except for gpt 5.5. You're dead wrong on that. You read too many benchmarks and/or chinese propaganda. There hasn't been a serious contender in agentic SWE besides OAI and anthropic for a long time, and no chinese model has even reached opus 4.5 performance yet. The moat isnt insurmountable but it is very solid for at least a 12 month lead time. Which is such an insane amount of time in…

All models from the past two years are close in the general case.

This is just another incremental improvement, rushed out to boost the ipo, AI has the capacity to aid an engineer but this minor bump in performance will have essentially zero impact on the productivity of an engineer working on real world solutions when compared with any other major model.

We are trending towards asymtotic and it can't happen fast enough, that's when the true cost of this will become evident.

Post reply on HN