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

Fable and the end of the free lunch

dbreunig.com

Post reply on HN
Print view View original

201–210 of 269 posts

Re: Fable and the end of the free lunch

#201

Post by lukan »

saghm wrote: post #194
lukan wrote: post #182

Earlier quoted context omitted.

Not if you let your LLM grounds its truth in established facts. Otherwise they would be useless for programming for example.

I don't understand what this means. I use LLMs daily for my work in programming things, and they regularly will assert things that are not accurate.

When you let the the agent do a test, or tell it to read that doc first, you will ground it in reality. Doesn't mean they are 100% reliable. But without and on their own without access to grounding information, they halluzinate wildly.

Re: Fable and the end of the free lunch

#202

Post by kay_o »

rmast wrote: post #57

Most of the things I work on are at least security adjacent. At some point chatting with Fable inevitably leads to it thinking about the security related aspects, tripping the safeguards. Maybe Fable can do the same things better than other models, but having to tiptoe around to avoid tripping safeguards makes GPT 5.6 so much easier to work with that I don’t even bother with Fable (or Opus 5) now.

I don't even need to tiptoe ! Not being there and not prompting anything is enough to trigger safeguards.

Having not asked a single security question it will write wildly vulnerable code, go back and fix it, and guardrail itself out of existence after charging me a large sum with no refunds for no output and having not fixed it because that might be secuirty adjacents.

And if it doesn't do this you end up with code that has such holes, store xss , no authz ... if it does not go back and notice it has written bad code.

Since they hide thinking and reasoning from the user (who is also paying for those tokens) it is a black box what is triggering it, has the LLM this time thought of "Oh, this has XSS" and used a bad dangerous word such as XSS, while the previous conversation did not ?

Re: Fable and the end of the free lunch

#203

Post by Varelion »

chinathrow wrote: post #183
peteforde wrote: post #77

A few months ago folks were understandably annoyed when Microsoft dropped their heavily subsidized per-request pricing model because it was figuratively burning cash. Well, I'm here to tell you that whatever is going on behind the scenes at Cursor with this Space-X acquisition in the works, the Auto setting is clearly routing all prompts through "Cursor Grok 4.6 High" right now. This is a degree of subsidy that makes…

Giving Elon cash seems still wrong to me.

Yea. I can't stress this enough -- my life would need to be unquestionably on the line for me to give elon anything other than grief.

Re: Fable and the end of the free lunch

#204

Post by stevage »

saghm wrote: post #194
lukan wrote: post #182

Earlier quoted context omitted.

Not if you let your LLM grounds its truth in established facts. Otherwise they would be useless for programming for example.

I don't understand what this means. I use LLMs daily for my work in programming things, and they regularly will assert things that are not accurate.

A lot like humans, really. People regularly cite something they read, or quote a stat that turns out to be just completely inaccurate. But if you look up the thing, then you have facts again.

Re: Fable and the end of the free lunch

#205

Post by cj »

bunderbunder wrote: post #199
nchmy wrote: post #2

The real revolution is Deepseek v4 flash and similar models (GPT 5.6 Luna, muse spark 1.2, mimo, etc...) - Genuinely good performance for a tiny fraction of the cost of Fable and even GLM etc... I think a lot of people would be very content if they never got smarter, and just kept getting even cheaper/faster. Of course, both things continue to happen on a seemingly monthly basis

But they don't really have that option. They're trapped in a Red Queen's race. The world keeps moving on, and so the models need to be retrained so that they can keep up with new information. Otherwise you'll get stuck with a model that only works well with information that existed prior to a dataset horizon that's receding into the past at a constant rate. At the same time, they have to keep iterating on the trainin…

> they don't really have that option

I imagine it must somehow be possible to update a model's understanding of recent events without training a completely new model from scratch?

Re: Fable and the end of the free lunch

#206

Post by ipsod »

peteforde wrote: post #77

A few months ago folks were understandably annoyed when Microsoft dropped their heavily subsidized per-request pricing model because it was figuratively burning cash. Well, I'm here to tell you that whatever is going on behind the scenes at Cursor with this Space-X acquisition in the works, the Auto setting is clearly routing all prompts through "Cursor Grok 4.6 High" right now. This is a degree of subsidy that makes…

How well does Cursor work with heavily agentic workflows?

I usually keep 4+ agents churning, many of them on tasks that take hours or day. I only played with Cursor a bit, but it seemed to want input from me every 10 minutes or so.

Re: Fable and the end of the free lunch

#207

Post by anthonypasq »

cj wrote: post #205
bunderbunder wrote: post #199

Earlier quoted context omitted.

But they don't really have that option. They're trapped in a Red Queen's race. The world keeps moving on, and so the models need to be retrained so that they can keep up with new information. Otherwise you'll get stuck with a model that only works well with information that existed prior to a dataset horizon that's receding into the past at a constant rate. At the same time, they have to keep iterating on the trainin…

> they don't really have that option I imagine it must somehow be possible to update a model's understanding of recent events without training a completely new model from scratch?

yeah its called web search

Re: Fable and the end of the free lunch

#208

Post by ninahaberl »

bunderbunder wrote: post #199
nchmy wrote: post #2

The real revolution is Deepseek v4 flash and similar models (GPT 5.6 Luna, muse spark 1.2, mimo, etc...) - Genuinely good performance for a tiny fraction of the cost of Fable and even GLM etc... I think a lot of people would be very content if they never got smarter, and just kept getting even cheaper/faster. Of course, both things continue to happen on a seemingly monthly basis

But they don't really have that option. They're trapped in a Red Queen's race. The world keeps moving on, and so the models need to be retrained so that they can keep up with new information. Otherwise you'll get stuck with a model that only works well with information that existed prior to a dataset horizon that's receding into the past at a constant rate. At the same time, they have to keep iterating on the trainin…

Models don't need to keep retraining just to stay current. Harnesses give them access to the internet, internal systems use RAGs, and so on.

I think lower-cost models will get the largest piece of the pie, as with almost everything that has ever been sold.

Just look at cars: US consumers buy the F-150, EU consumers buy the freaking Dacia Sandero the most :)))

Ferrari/Lambo numbers are microscopic

Re: Fable and the end of the free lunch

#209

Post by zdragnar »

ninahaberl wrote: post #208
bunderbunder wrote: post #199

Earlier quoted context omitted.

But they don't really have that option. They're trapped in a Red Queen's race. The world keeps moving on, and so the models need to be retrained so that they can keep up with new information. Otherwise you'll get stuck with a model that only works well with information that existed prior to a dataset horizon that's receding into the past at a constant rate. At the same time, they have to keep iterating on the trainin…

Models don't need to keep retraining just to stay current. Harnesses give them access to the internet, internal systems use RAGs, and so on. I think lower-cost models will get the largest piece of the pie, as with almost everything that has ever been sold. Just look at cars: US consumers buy the F-150, EU consumers buy the freaking Dacia Sandero the most :))) Ferrari/Lambo numbers are microscopic

Even with a harness, models don't reach out for new information they don't know about. For some tech, I have to have a local model draft a plan, then I have to adjust the plan to update it with the new API and references for where to find it. Even if I include that updated information in the prompt for the plan, the model says "what the user says is wrong, they probably meant this instead" and goes off in its own direction with old APIs anyway.

Re: Fable and the end of the free lunch

#210

Post by fidotron »

HighGoldstein wrote: post #200

I find it somewhat funny that the author starts by talking about how Moore's law enabled inefficient software and that we then had to make it more efficient, when almost all software today is horrendously inefficient compared to even 10 years ago, let alone 20-30. We've somehow even achieved a state where it doesn't matter how fast your CPU and memory are, the software will just perform horribly on any machine.

One of the funniest parts of the LLM wave is discovering that cron was so annoying to use that we will burn the planet to put an interface on it that people can actually work with.

The tendency for absolute inefficiency is effectively unbounded until scarcity is imposed.

Post reply on HN