Earlier quoted context omitted.
How is the harness broken?
its bloated, try /radio
[dead]
Fable 5 is Back
151–160 of 438 posts
Re: Fable 5 is Back
#152Glad it's back, but the price outside of the subscription is insane. API pricing is just not for regular users.
Re: Fable 5 is Back
#153I was wrong, I thought they would only go for B2B already. But instead they will remove it from the subscription and price it at 50$/mtok. Compared to GLM-5.2 for 4.40$ that's quite a gap
how does GLM-5.2 fare against fable/opus 4.8? I am thinking about moving my 5x subscription either towards the GPT equivalent or the GLM one (I heard GLM gives you 20x the token usage for the same price of anthropics 5x)
Re: Fable 5 is Back
#154Earlier quoted context omitted.
If it's API pricing, I'm going to ditch Claude Code and switch to a harness that can jump between GLM and Claude Code. Cheap pricing is why I use Claude Code. The minute they fumble that, I'm using Chinese models for 90% of the work.
how can a harness switch between glm (a model) and claude code (another harness)?
I've been doing this for ages - you just spin up harness B as a subprocess/tool call from harness A. For example, I had a "/codex-review" claude skill for ages that did exactly that. Technically you're right it wouldn't be switching, since you're right the two ideas are at different altitudes, but I think in practice it has the same impact: within one harness, you can delegate certain tasks to certain models or harnesses.
Re: Fable 5 is Back
#155I have to admit that when it was blocked, I canceled my max plan and asked for a refund. It felt like someone took away my previous toy. So I'm happy it's back again; I upgraded to max again. Coding aside, but Claude Design is phenomenal - for both new designs and redesigning existing UIs. So my customers will face a new wave of refreshed screens all over the place in coming days ;)
[flagged]
Re: Fable 5 is Back
#156Earlier quoted context omitted.
That didn't take long... Dynamic workflow "Multi-lens review of docs/membership-and-friends-model.md with adversarial verification" completed · 25m 59s You've reached your Fable 5 limit You've used your included Fable 5 usage for this week. Continuing on Fable 5 uses usage credits
Wow, practically totally useless.
This doesn't have a Max 20X upgrade path for me https://claude.ai/upgrade, but this does https://claude.ai/upgrade/max/from-existing
Re: Fable 5 is Back
#157Earlier quoted context omitted.
That didn't take long... Dynamic workflow "Multi-lens review of docs/membership-and-friends-model.md with adversarial verification" completed · 25m 59s You've reached your Fable 5 limit You've used your included Fable 5 usage for this week. Continuing on Fable 5 uses usage credits
Managed to hit 100% of my 5 hour limit and 19% of my weekly Fable limit in 12 minutes. I have a Max 5x subscription. Can't wait to try out GPT 5.6 at some point when it comes available.
They just reset the weekly limits (Max 20x)
Re: Fable 5 is Back
#158I deleted my claude account the day the samples started preaching from the pope’s address and claiming 50% of the jobs will be gone while shamelessly stealing entire corpus of human data without attribution while preaching what you can and cannot do and maliciously degrading model quality.
I hope they either never make it to IPO or crash violently.
Re: Fable 5 is Back
#159Earlier quoted context omitted.
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.
Your vibes are definitely better than his vibes.
What about all the benchmarks that show improvements in each generation?
Re: Fable 5 is Back
#160Earlier 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.
4.6 was the last model that let you disable adaptive thinking and set max thinking token budget. I liked having that available, and still use it sometimes.