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

Fable 5 is Back

twitter.com

Post reply on HN
Print view View original

171–180 of 438 posts

Re: Fable 5 is Back

#171

Post by Kiro »

stavarotti wrote: post #80

I'll be using it tonight but grudgingly so. Grudgingly because after July 7th, I'm not going to all of a sudden, start paying API prices (and maybe that's the problem) when I'm used to a subscription that gives me multiples in comparative value. Perhaps this is the fabled "token economics will come for everyone this year" that I've been reading about? In any case, I'll use the hell out of it to extract as much as I c…

Won't using it eat up the whole quota immediately forcing you to pay API prices anyway?

Re: Fable 5 is Back

#172

Post by madamelic »

pkoird wrote: post #144

I gave it a book on human consciousness I was writing and it flagged it. This model is hilariously bad. Anthropic has defanged this model to the point of malice. No way am I paying to use something that is basically useless.

Today I told Sonnet (!) to use a browser MCP to enter a username and password for the project it is working on, it told me that it can't do that because it violates its security protocol.

This worked fine before. I love Claude, I have stuck with it even through people saying Codex is better but this is definitely getting to be the last straw.

It's completely absurd I am paying them $200+ per month along with pushing them when I do contracts and they can't even deliver a baseline respectful service.

In 6 months I am sure they'll only allow me to talk about Easybake recipes and after someone gets burned on the lightbulb, they'll downgrade it to discussing wildflower meadows.

Re: Fable 5 is Back

#173

Post by digitaltrees »

dymk wrote: post #159
dandellion wrote: post #148

Earlier quoted context omitted.

Your vibes are definitely better than his vibes.

What about all the benchmarks that show improvements in each generation?

Many of the improvements are the result of agentic loops and an emphasis on autonomy. Some of us don’t like that because the models go rogue and ignore design patterns, architecture, coding guidelines or other things that are important.

My friends and colleagues that like the agentic autonomy don’t care about the code, they feel like if it works it works and if an AI system is the only intelligence able to understand it that is ok.

I still want to be in the loop. They don’t.

Re: Fable 5 is Back

#174

Post by solenoid0937 »

jatora wrote: post #136
matltc wrote: post #111

Earlier quoted context omitted.

I locked my default model to opus 4.6 around the time of the nerfs. Such better results compared to 4.7+ That's enshittification for ya I guess

The claims of 4.6 or 4.7 being superior genuinely make me laugh. Adapt your workflow if needed and use the superior model instead of just kneejerk believing they actually enshittified a model with zero evidence except vibes on an undeterministic model output. Jesus.

4.8 is much better than either of them as well.

Re: Fable 5 is Back

#175

Post by signatoremo »

vonneumannstan wrote: post #119
trunnell wrote: post #112

Their post detailing the timeline and their actions since reinforce my belief that Anthropic is among the most trustworthy AI companies. https://www.anthropic.com/news/redeploying-fable-5

Its like saying Pinochet was one of the least murderous authoritarian dictators. The bar is low...

Where are Chinese companies on your scale? Mistral?

Re: Fable 5 is Back

#176

Post by digitaltrees »

bel8 wrote: post #108
dghlsakjg wrote: post #60

Earlier quoted context omitted.

OTOH: “our product is so good it was banned for being too good” is the best advertising possible. OpenAI would kill to get that. I’m not falling over myself to test out Sonnet 5, but I am very interested in Fable.

> OpenAI would kill to get that. I have news for you, from 5 days ago. https://news.ycombinator.com/item?id=48690101 "U.S. government will decide who gets to use GPT-5.6"

First mover got all the power of the narrative.

Re: Fable 5 is Back

#177

Post by steve-atx-7600 »

aliasxneo wrote: post #6

> Until July 7, you can use up to 50% of your plan's weekly usage limit on Fable 5. If you hit your limit, you can continue on Fable 5 with usage credits. Fable 5 draws down usage faster than Opus 4.8. This is what I see in my Claude Code terminal. I don't feel like that 50% rule was there before?

Opus 4.8 is so slow vs gpt 5.5 that even if it is marginally better, it doesn't matter for my daily engineering work. gpt 5.6 will be out soon and codex 249$/month plan has been incredibly generous. Paying the alleged new cost of fabel 5 would require it to be much better that I remember when I used it last.

Re: Fable 5 is Back

#178

Post by Citizen_Lame »

This is pure nonsense. I asked it to edit one (long) html file, and it used up 5 hour session limit and it didn't even finish. For comparison, same task with Gemini Pro 3.1 Thinking took like 5% of usage. Similar with Codex 5.3.

Strangely enough, cancelled the subscription listed the reason, and after 15 minutes session limit is back to zero.

Re: Fable 5 is Back

#179

Post by bob778 »

xtracto wrote: post #129
petra wrote: post #26

Maybe, for some projects, instead of generating code with it, it would be useful to generate a plan and the loop(tests/formal verification),because those take much less tokens than a full project, and than use the loop using the older models ?

Has anyone experimented with Batch Processing? According to https://claude.com/pricing#api using Batch processing cuts the price 50%. So I wonder if any of the harnesses like OpenCode/Pi or similar could be made to use that for planning or similar.

Batch can take up to 24 hours (and often does) and may never complete if it gets cancelled so it’d be hard to build a user workflow around unless you kick off planning on Friday and come back Monday
Post reply on HN