Sabitlenmiş Tweet
Some of you said it still looks like AI slop, and I agreed, so I told Fable to "100x the design."
Here's what it did, and all the details on how.
Anshu@anshuc
English
Anshu
2.2K posts
Anshu
@anshuc
Posting about how to build beautiful apps and products with AI. Let's end slop together. Formerly: YC founder, UI/UX & AI @apple
SF Katılım Haziran 2009
1.1K Takip Edilen3.8K Takipçiler
@synthwavedd in the midst of "we’re so back", I found there was, within me, an invincible "it’s so over"
English
🚨 SCOOP: Use your Fable 5 quota while it lasts.
Anthropic are working through the final stages of preparations for the launch of Claude Opus 5, with plans to launch as early as later this week (this week and next week encompass the 2-week target window).
As it stands, they are *not* intending to extend Fable's inclusion in subscriptions beyond July 19th. A successor to Fable 5 is planned for August to compete with GPT-6, and for now they think they can get away with launching an Opus model not too far from Fable but cheaper to serve.
English
@yessabhishek You can just slide the slider to their follower counts, though it would be nice to have some presets
English
@exponent818 of course, it’s my privilege and duty as a lowly human to contribute my private data to the grok archives
English
@0xdominus They’re pretty different models. Hard to compare. But yeah if they lifted the restrictions and stopped being so bad at communicating, I think public opinion would favor Fable. It’s done more impressive things for me than Sol so far
English
@anshuc Quick question. The recent opinion has been that Sol is slightly better.
Do you think if Fable didn’t have so much restrictions, 5.6 Sol would still beat it?
English
Here's GPT-5.6 Sol vs Fable asked to build the exact same app (prompts in the article!)
What do you think? I have my opinions, but I'd like to hear yours.
Both built complete, working apps, but with very different approaches:
- Sol took less than half the time at the same (high) reasoning
- Sol spent much less time on frame analysis. Fable dumped sheets of frames for every transition and scrutinized them multiple times; Sol only checked twice, and both times was just like "looks great, continuing"
- At first, Sol intentionally ignored my request to use image generation! It went with procedurally generated food images "for simplicity" (they looked terrible)
- On the second prompt, Sol generated images, but intentionally ignored my suggestion for transparent image backgrounds, saying full photos "preserve shadows more convincingly"
- Sol's used its built-in GPT Image 2 integration, which saved cost; Fable had to use the Gemini API
- Sol didn't seem to know how to use Liquid Glass at all
- Fable was more restrained; Sol wanted to add extra labels and detail
- On the other hand, Fable decided to add an extra detail page for foods, while Sol did not
- Both had nice haptics on device
- Fable added a pinch dismiss gesture; Sol did not do gestures
Anshu@anshuc
English
grok claims it accurately models the compounding dynamics of a growing X audience, or something
link: notification-gravity.anshu.dev
English
@danieloleary I definitely felt this with 5.5, to the extent that I put stuff like “literally just do what I say, your job is to just do exactly what I tell you” in my Codex instructions, and even then it’d ignore me. I’m not sure yet if 5.6 is any better…
English
@anshuc I feel you. Had to tell an image heavy project today “You aren’t listening to me. I am going to unplug you”.
That seemed to do the trick….. for now
English
@KevinTungDesign I'd mostly agree. The inconsistent text alignment bothers me a little with the Fable one. But the gigantic images in the Sol one feel like a poor use of screen real estate. Fable is definitely closer to what I had in mind writing the prompt
English
While waiting for Sol to finish coding, we need a tiny game or puzzle to keep us entertained.
Win a round → get some weekly quota.
Keep winning → unlock extra resets.
Anshu@anshuc
if the models are gonna be celestial bodies, the model picker should be a rocket
English
@sir_franco_ Yeah, I can see how the Fable one is overwhelming with text. The 5.6 one feels like it doesn’t use screen real estate that well though, with the huge images. Maybe something in between these designs would actually be best
English
