alex

instant skip when I see this @nikitabier saving this platform

Grok 4.5 is really good wtf

new product is starting to see crazy traction slowly reducing ai costs and improving margins, currently at 60% and looking to increase this a little more

@1x_tech keep Kim K away from this one

NEO’s Hands An API to the Physical World

me: you forgot to handle x opus: good spot - let me ground myself in what has happened fable: already done boss

my general philosophy is work smarter not harder and that applies to my model of choice I’d prefer to use a model which completes the task better and with less steps. Whether the model can keep going for days is completely irrelevant if it wastes much of that going around in circles

My view of: Fable 5 vs GPT-5.6-Sol. They are not easy models to compare, these are my vibes - take them as you will. My overall feel is that Fable is a 'wise owl' who is very thoughtful and very well spoken, GPT-5.6-Sol is like a rottweiler who will grab the problem by the throat and not let go until it is done. In other words, Fable, is a fundamentally smarter model - even at low reasoning it can be very insightful and writes in a clear compelling way. GPT-5.6-Sol on the other hand is extremely diligent, I can give it a list of 8 things to do and you will be sure that they will be done. Fable feels more arrogant to me, I was both to get it to build a new benchmark for me - 5.6 worked between 6 hours and 2 days (I tried several times) and it came up with very thoroughly tested, working benchmark. Fable came back within 40 minutes (twice) and the benchmark sounded smart, but was ultimately was 'vibe' based slop and since it was Fable's vibes that was doing the judging, it decided that it was good to go (it kept giving Fable 100% score btw). Some thoughts by category: UI & App building: Fable will still craft a better UI from scratch, the flow of the app would probably be a bit nicer. But I find that Fable often misses quite key things, which GPT-5.6-Sol doesn't. GPT's Frontend skills are big jump vs previous GPT models, but still not as great overall. Writing: Fable is better hands down, Sol feels quite difficult to align to what I want to say or explain things to me simply. Though I think the 'Pro' model writes clearer. Robustness & Reliability: This is where I think GPT-5.6-Sol wins for me hands down. Fable seems to do things of high quality, but I can never relax with it, it always misses something. With 5.6 this just almost never happens. Other things where I liked GPT-5.6-Sol, but can't compare to Fable directly. - Video editing is actually working now, it is not completely perfect, but with the right skill/guidance you can just give it 1h footage and it can give you a 5 min highlight clip no problem - Computer use - getting really rather good, very usable - Sub agents - it is very fluent at managing sub-agents and speaking to different threads, can help with some new workflows - Adhering to existing code patterns - I love this, even without asking it would implement something in a way that aligns with you app - major problem for slop generation - Research - I think it is getting quite a bit better, it still has some bad patterns (e.g being too tactical), but it feels like it is more steerable to be a good researcher - Multi-day runs - the /goal feature is pretty insane with 5.6-Sol, you can run it for days if you wanted to and it does work. Useful to have another thread or /side to check up on it, but I have some great results with it - Token efficiency - it is so much more token efficient and faster than 5.5, in reality it is now much faster than Fable too On the downside, you can feel that Fable is naturally smarter, and I did have some baffling moments with 5.6 when I was getting it to make a fairly simple change in 8 turns - it seemed to get stuck in a dumb stream that was hard to get out of. So it is not AGI, don't get too carried away by the hype. I have some phenomenal examples that I'm honestly blown away by that I'll share, but as a side anecdote, I have a kind of 'swear meter' which counts how often I'm rude to Codex. In GPT-5.5 era, the % was at around 4-5%, it dropped to 1-2% when I was testing GPT-5.6-Sol and it shot up to 7% when I went back to 5.5 - it was so shocking to go back to 5.5 and experience how much worse it was. So is GPT-5.6-Sol better than Fable? On pure intelligence - no. But man, I missed it when I just wanted to get sh*t done. It is insanely capable workhorse that you can give any task to and just expect it to be done. No lectures or 'you are absolutely rightisms', nothing is beneath it, if it takes 2 days to do some dirty work, it will do it. It feels like the first time in a while when we have quite different types of frontier intelligences that benchmark sort of similarly, but feel very different. If you can, you would be probably better off using both and iteratively finding what you'd use Fable or GPT-5.6-Sol for. Perhaps, something like - an architectural discussion with Fable, implementation with 5.6 and docs & comms with Fable.

@mitchellh lol this used to be the reverse prior to fable

I had early access to 5.6/Sol for ~month. Sol is my default. It is faster, plans/judges just as good as Fable, and I think produces better overall work. I’ll reach for Fable still for highly targeted debug or performance work with clear reward functions. A cheeky way I describe Sol vs Fable to my friends is that Sol is a charismatic, efficient, talented coworker you’re jealous of. Fable is a genius recluse that is brilliant at its fixations but doesn’t go out, doesn’t date, and you don’t want to hang out with them much lol. Fable is undefeated at highly targeted debug/security/performance goals. It’s a sight to behold and I was never able to get Sol to push as hard in this category. I’ll keep using it for this. Sol is better or comparable at everything else, in my experience. Give it a shot, it’s hard to describe but it’s just more enjoyable to work with. (Disclaimer I have no financial ties to either lab, wasn’t paid for any of this.)

pair this with fable /advisor mode and it’s pretty damn good for opus replacement

sonnet 5 is a great model for day to day boring work it is now powering all the scheduled tasks for new product

@claudeai YEEEEEAAAAAAHH BUDDDY

We're extending access to Claude Fable 5 on all paid plans through July 12.

this isn’t true anymore in b2b you are now fighting against the non technical executive thinking they can just vibe code you this alone will make your sales cycle 1000x harder to close

the only thing that will slow you down now is working with others it’s the age of the solo founder

my new product is now running in a loop ads, analytics, errors, usage etc all feeding into claude every day it either creates a new PR or actions something I’ve given it a goal to optimise for so I think it’ll keep running in this loop until we hit the next financial milestone or wall this is essentially 3 harnesses coming together around engineering, product and growth crazy stuff

burned through usage for two cc accounts in 5 days ama

the biggest alpha when building any new product right now is building a harness for self improvement analytics, usage, errors, revenue - give Claude visibility to all of that and you’ll be shocked at the results

I didn’t understand the idea behind these commands now I use /rewind every time it reminds me of learning how to rebase, cherry pick and being able to bend git history as you needed /rewind /fork /compact are all useful in their own ways

using fable, i monitor my 7 day usage bar like my single session context window size

@robj3d3 if you use workflows, fable will handle all of this automatically and one shot every time > ask what you want, interview to avoid assumptions and pipe to a spec doc > use workflows to implement and verify yourself

Fable 5 has been re-released with 50% weekly usage. Copy my output-optimized Fable stack that doesn't burn tokens like crazy: > [I explain the task] > explore - scout agent (Opus, low) > plan - Fable high > [I review the plan] > implement - Fable medium > diff review - Opus high, fresh context > [I review the implementation] > save progress to md, /clear, next phase I use 3 Claude agents: - scout.md - implementer.md - reviewer.md Save them at ~/.claude/agents/[agent].md Along with CLAUDE.md at your root folder to orchestrate the whole thing. Fable never reads raw files (scout does) and never reviews diffs (Opus does). Reserve Fable's intelligence for planning and building. Everything else is a token sink. Big tasks get split into phases. Progress lives in a md file, not the chat. All prompts shown below. Feel free to copy and adapt.

Pro tip, use Fable low effort. Still way more powerful than opus 4.8 on extra high Use sonnet 5 with advisor mode reaching out to Fable when it needs help for daily stuff Save super saiyan fable mode for hard things

thank you