Sunny

@jasondoesstuff @thsottiaux @sama

I've been using Fable 5 and GPT-5.6 Sol A LOT the past few days. Both on effort level high. Three different projects with vastly different codebases. Some thoughts from real-world use... 1. Fable 5 **never** makes mistakes. Not once. I've given it complex features and it never randomly messes up. It's actually blown my mind a bit. 2. GPT-5.6 Sol gets it right 50% of the time. It hasn't deleted any production code, which is great, but it also makes stupid mistakes and just forgets to do part of a feature entirely. I find myself having to go back and forth with GPT-5.6 just as much as I did with GPT-5.5. 3. I built a Captions feature into our video editing app (SceneRoll) in two separate workspaces, one with Fable 5 and one with GPT-5.6 Sol (same starting prompt). Fable 5's was nearly perfect out of the gate (a couple small UI tweaks). GPT-5.6 Sol didn't even have the captions playable on video 😂. I spent an additional hour and then finally just gave up on GPT. 4. Fable 5 thinks about a lot more edge cases. It's going 4-5 steps further without telling it to even do that. 5. GPT-5.6 Sol does not think very far ahead. Yes, it's better than 5.5, but I wouldn't say noticeably. 6. Fable 5 is a more creative thinker. I asked it build a gamification trial onboarding flow for our content creation app (Solo Content Studio). It was REALLY good. It thought through little animations, details, and even small alerts to give to the user. 7. GPT-5.6 Sol can work within a brand system well, but it does deviate randomly. It LOVES trying to shove a dark mode moment and random shapes into a page. Fable 5 never does this. It just follows the brand system and never invents any random design treatments. 8. I am NOT A DEVELOPER, so take this with a grain of salt: GPT-5.6 Sol writes more code than Fable 5. It seems to just try to do more or write more, when it really doesn't have to. On a feature that's 1,000 lines of code, Fable 5 usually removes 15% of what GPT-5.6 Sol wrote. 9. GPT-5.6 Sol wins by a mile on actual usage. Think of it like a Toyota Prius. It's going to give you 80 MPG and you're never going to need to worry about your usage. Fable 5 is like a (token) gas-guzzling SUV. You feel how much usage it tears through. 10. I used "Ultra" mode on both. I'm not entirely sure I see the point, unless you just want to YOLO your usage and have it work on something big overnight. I would only trust Fable 5 to work overnight in Ultracode. It would nuke usage, so I'd rather just babysit it during the day and get a lot more done with the usage. 11. I have a 13-year old codebase (Teachery) that I've tried to use GPT-5.6 Sol on multiple times, and multiple times it cannot do the simplest of tasks correctly. I don't know if it's just getting lost in the old spaghetti code or what, but it fails to do simple things like take a list of 140 users, only show 15, paginate the rest. Fable 5 accomplished this in 1 sentence and 1 attempt. GPT failed 3 times on this task. 12. Unrelated to code, I feel like Fable 5 and GPT-5.6 Sol are on the same playing field when it comes to brainstorming, analysis of data, and big picture thinking. Neither feels better than the other. 13. Oh, when you give GPT-5.6 Sol a complex task, it will spawn ONE MILLION AGENTS 😅. It's actually kind of insane. I don't care that it does this, but I find that Fable 5 feels more conservative with its agents. It uses them, but it doesn't just whack 20 of them onto tasks. FINAL THOUGHTS... The takeaways above, were based on singular use with each model. My typical building flow is Fable 5 as planner/reviewer, GPT-5.6 as code writer, Fable 5 deploys Opus/Sonnet as agents to verify and test. This is the best way to squeeze the most juice out of both models (and really, just save as much Fable usage as possible). Like many other people, I'm going to be sad to see Fable 5 goes to usage credits only. My hope is that Opus 5 ends up with all the same reasoning abilities, and can orchestrate and manage big tasks like Fable 5 does. But, being totally honest, if I have to pay $200-$500 in Fable 5 usage credits a month to continue to use it with sky-high confidence and accuracy, I’ll do it in a heartbeat.

Codex success must be stuied. I created a graph showing how usage figures increased after the GPT-5.6 release (maybe I should also make a graph showing the exponential increase in resets).

Hurry up, Mom will be home soon.😂

This is how I work 25 jobs at once. Don't tell anyone

@thsottiaux bank a credit more worth it

Embarrassment of riches. But looks like we might hit 9M soon. Should we reset the ChatGPT Work and Codex usage again or give it some space?

@thsottiaux you removing the 5 hour rate limit feels awesome. feels like removing handcuffs. chatgpt desktop is also awesome, many integrations. what i miss is subagent control, forked agents, fresh context agents, scouter agents, need to work more on ui and specialised agents.

Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched? Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens! switch-to-codex.openai.chatgpt.site

The difference between a dog and a cat

uhm this gpt 5.6 launch might be the openai's most successful model ever since... since chatgpt? this is IPO altering stuff going on here

This explains a lot of takes before the algo change

🚨Japan is based as f*ck! Japan's new laws send shockwaves!! Halal - BANNED✅ Mosques - BANNED✅ Call to prayer - BANNED✅ Burka - BANNED✅ Should we copy Japan?

A mother asked her kids to recreate how all 3 got on top of the wardrobe. You wouldn’t believe your eyes 😅

microsoft, adobe, any boomer saas business' lifetime is a function of gpt's tok/s

they’re right about the permanent underclass but it’s the people who refuse to or can’t use ai effectively, not the people who own it

@aight_cun @TimJayas im so sure he didnt test all latest sota models extensivly and just wants to share their opinion

@_sunnymind @TimJayas Not skill issue, if you have done any kind of actual creative writing, it couldn't be more obvious which is the best.

GPT-5.6 Sol beats Fable in Creative Writing Benchmark though i personally find GPT 5.6 Sol not better than Fable or Opus claude has much better defaults and needs way less prompt engineering for writing emails, blog articles, stories, presentation scripts...

BREAKING: IBM stock, $IBM, collapses nearly -20% after posting weaker than expected earnings due to “weakness in the software and infrastructure business.” The stock just erased -$55 billion in market cap.

if deepseek, kimi, and gemini all drop this week anthropic will have 7 competing models all better than anything they have for ~5-10x cheaper

Every single AI startup with $500M+ revenue run rate (excluding the big 3 labs): Lovable - $500M ElevenLabs - $500M Perplexity - $500M Manus - $500M* Cognition - $500M* Kling AI - $500M Crusoe - $500M* Midjourney - $500M* Higgsfield - $500M Lightning AI - $500M+ Replit - $525M* Baseten - $600M* Lambda - $760M* Fireworks - $800M* Together AI - $1B Surge AI - $1.4B* Scale - $2B* Mercor - $2B** Cursor - $4B 22 total companies (including big labs) *estimated / unconfirmed **gross marketplace volume, not net revenue

@aight_cun @TimJayas probably skill issue

@TimJayas Nothing is better than Opus 4.6 in creative writing.

@TimJayas this is unexpected