That's hilarious. Does OpenAI even know this doesn't work?
That's hilarious. Does OpenAI even know this doesn't work?
I've been arguing for some time now that it's the "organizational world model," the accumulated process knowledge unique to each company that's genuinely hard to replicate. I did a full "report" about the six-layer decomposition here: https://philippdubach.com/posts/dont-go-monolithic-the-agent...
Currently integrating an AI Assistant with read tools (Retrieval-Augmented Generation or RAG as they say). Many policies we are writing are providing context (what are entities and how they relate). Projecting to when we add write tools, context is everything.
The article does provide a hint: "Operate". One needs to get paid for what LLMs cannot do. A good example is Laravel. They built services like Forge, Cloud, Nightwatch around open source.
OpenAI's strategy is to eventually overtake search. I'd be curious for a chart of their progress over time. Without Google trying to distort the picture with Gemini benchmark results and usage stats which are tainted by sheer numbers from traditional search and their apps.
We therefore connected Serif, which automatically writes drafts. You don't need to ask - open Gmail and drafts are there. Serif learned from previous support email threads to draft a proper response. And the tone matches!
I truly wonder why Gmail didn't think of that. Seems pretty obvious to me.
- Servers you can run what you like on – VMs, bare metal, etc.
- Containers that you can put what you like in, but which run in some system you don't control – Kubernetes, ECS, even things like Heroku are here now.
- Language specific micro-plugins, where a small piece of code is hosted in a common server process – AWS Lambda, Cloudflare workers, all the FaaS stuff. These are sometimes language specific, but I expect them to align on WASM.
Being PHP and Laravel specific doesn't really fit any of these, it's a model that sort of existed around the early Heroku days, but seemed to lose out to first Heroku and its generic buildpack system, and then eventually to containers.
What happens when a team wants to add a little Node process for some frontend thing? Do they need to move their entire hosting? Who is the target audience of a provider like this, and perhaps more importantly, can they stay with a provider like this for very long?
I run a B2B SaaS on Laravel and this was a dream of mine for many years. Laravel + Vuejs is sufficient to cover 99% of features we need to build and scale our business. I want my devs to build features, not infrastructure.
I'm looking forward to playing with Laravel Cloud and do hope we can migrate our production environment to it one day.
I can't wait for Atlassian physical sticky-notes to take over.
[Edit: grammo and formatting]