I've been building something quietly for some weeks. Today I'm sharing it for the first time and honestly I'm nervous.
KreatorMesh: post one video to Instagram, LinkedIn and X at once. No more uploading the same thing 3 times.
Here it is, working
I've been building something quietly for some weeks. Today I'm sharing it for the first time and honestly I'm nervous.
KreatorMesh: post one video to Instagram, LinkedIn and X at once. No more uploading the same thing 3 times.
Here it is, working
@FinPlanKaluAja1 I mean, I get the point you’re making.
But just so you know, engineering graduates in Nigeria aren’t trained to repair generators; they’re trained to design them. That’s the role engineers are educated for. Polytechnic graduates, on the other hand, are typically trained for that
Quantum Instruction-set languages (OpenQASM, Quil) sit close to the hardware, providing low-level gate sequences that quantum processors can execute directly. Powerful, but requiring deep knowledge of quantum gate design.
Here's a simple loop: Tell codex to maintain your repos, wake up every 5 minutes and direct work to threads. That makes it easy to parallelize+steer work as needed.
I use a orchestrator skill combined with my triage+autoreview+computer use skills, so some work can land autonomously. https://t.co/FbBoJTIcfd
https://t.co/8389roVnOm
I am sorry in a world where there’s a Fable, why will i wanna use something else? limit resets in 5hrs anyways, most times i hit the limit 1hr to reset.
You should basically never use Fable for coding, but instead use it as a planner/orchestrator.
Most of today's advanced models can implement a spec perfectly, and once done you can send the work to Fable to review.
This has been my most powerful flow so far.
You should basically never use Fable for coding, but instead use it as a planner/orchestrator.
Most of today's advanced models can implement a spec perfectly, and once done you can send the work to Fable to review.
This has been my most powerful flow so far.
The problem is, some of these models have quirks that need to be handled individually per harness. Every team should be aiming at building their own internal agent harness or use harnesses that aren’t tied to a particular model provider.
Trusting any single AI vendor seems like an increasingly high risk for any team or company.
When using models: use it behind a router where it's trivial to switch providers as soon as one tries to force unacceptable T&Cs like Anthropic with Fable. When using harnesses: do the same. Use ones where models are trivial to switch out, like OpenCode, Factory, Cursor and many others.
Putting all your dependencies on one provider increasingly feels like a massive business risk that makes little to no sense to take.
Unless you have a hobby project, of course. Then convenience is all that matters. But if you're a professional, make it dead simple to offramp from one provider to the other!
Things I really dislike about Fable:
1. Anthropic collects my prompt history, stores it, and does whatever they want with it for 30 days. No opt-out
2. They can nerf their most expensive model without telling me, billing me the same amount, wasting my time. Whenever they want