This thread is so spot on but I can also imagine the product development internally is moving so fast that they're trying to reconcile everything and can't. And this is the huge mistake so many companies make. Leave what's working alone. Build new adjacent things. It's clear they want to make money and work or code is the focus of enterprise. But never rename something Classic...so bad.
Ah interesting. So I'm using an English translation. Tbh I wish I could do more with the Arabic but the models are not perfect at that. But the idea of giving it whole paragraphs makes a ton of sense.
Tried to generate audio but wasn't satisfied with the interpretation of some words, saying that thou may try again.
That's cool! I did the same for the Quran to see how RAG works. I also indexed related works called "Hadith" and the names of Allah. It initially required indexing everything using OpenAI embeddings and then powered by it.
In case someone is using something we haven't heard of e.g some are running using cloudflare workers which also has some unique runtime properties. AWS has something called LLRT.
Curious to know who is using Deno in anger most days and in production full time? It seems like the choice of JS runtimes exploded over the past few years with that, Bun, etc.
I wrote recently about bringing back my open source project back from the dead. It's more than a decade old. Many life events occured during that time. It's tough. It's nothing like Lodash but honestly these things ebb and flow. It operates in cycles just as life does. Wish him all the best. Sounds like he had many tough years personally and I can relate.
This was my assumption. Agents will supersede services. There will be many companies way ahead of the curve and the rest of the industry will take 5-10 years to catch up.
> The traditional startup growth arc assumes that the path from idea to scale
is validate → raise → hire → build → raise again → grow → hire more → repeat.
Now, AI has erased the expectation that each new phase in the startup lifecycle
requires a bigger team, a different skill set, and a fresh funding round.
From 2015-2019 I spent the whole time saying "If I don't write the code nobody does". It was the point of saying to do anything requires a team, to build that team you need funding. It was a vicious cycle and took a long time to get enough traction to raise funding and do that... and then you end up in the MVP loop -> hire -> build -> validate -> rehire -> rebuild -> revalidate. Today all of that has changed. You don't necessarily need the team to write the code, it's for a different function entirely, maybe the original function which is the team was the orchestration engine for all the different pieces at play to make a company and product successful. The code is only half the equation. Looking forward to seeing how solo entrepreneurs leverage these tools and how teams transform using them.
I don't run local models, my devices are 5-6 years old and not powerful enough. It's a bit counter intuitive and different to what a lot of engineers are doing but I don't have a mac mini, I don't have a powerful laptop, a lot of my dev work has always been cloud based, on github, on a VM, I'm mostly using SSH from my laptop and now Claude Code on my phone (exe.dev is hands down the best experience I had on this front when the agent is literally on the VM).
In an ideal world, yea you can run local models, but I need a powerful always on device for that, or the latest gear, and it will never be as fast as what I can use from google, anthropic, or through an API call. I really wish it was different but I have to shell out a ton of money for that, and I guess it's usecase specific right. Maybe if my phone was super powerful and could run models that would be great, but then I have this issue with cloud sync and using things anywhere else. There will be a world in which local models and self deployed models make sense, this is going to be a core experience, but I personally can't run them.
Wow. So a deal like this is not overnight, its 6-12 months in the making at least. So the name change comes as they knew the deal was closing and doubled down on this new branding for customer agents. Maybe because Saleforce wants Salesforce Fin Customer Agent as a product. Who knows. Don't want to read the post...
Personal AI. Step by step evolving something I worked on for 10 years from an open source Go framework to APIs to apps and now agents. It's been an interesting journey. It's not finished yet. It's also not going to be a billion dollar company or have breakout success like OpenClaw but when you tackle personal problems I think they turn into more valuable opportunities. The opportunity to learn or have something that benefits a few people. I can't take off my entrepreneurial hat though. I keep trying to figure out how to make it work for everyone but I think that's the trap. Build for yourself. The rest will come.
Originally I felt there should be an alternative to Google and Facebook. It felt like our lives were being ruled by tech giants even ten years ago..and then all the advertising and algorithms really messed with us. I personally wanted an alternative way to use the web. So it's based around what I'd use on a daily basis. And then the idea of being able to extend it with a native app builder. The big stuff I continue to build with Go but ad-hoc things I can knock out with some JS in the app itself.
Reminder.dev - Quran app and API that includes RAG search to provide a more authenticated source of summarisation. The first thing I dabbled in with AI.
Micro.mu - Rebuilt my entire product idea from 10 years ago as a super app for daily digital habits. Something I use everyday for myself.
Aslam.org - An islamic knowledge base that uses sources of data as a way to ground AI chat and make notes. Very useful tool that I'm using on a daily basis.
Go-micro.dev - Totally revamped the open source project, docs, etc with Claude.
I think there's a lot that doesn't get built initially especially around error management and more feature completeness around how the response will be shaped. I think it's an interesting demonstration in how to leverage an existing system of services for AI but definitely more to do. Thanks for asking.
Edit: One other thing I kept out was code generation — the agent can call services but doesn't create them. I've just built it: `micro run --prompt "a task management system"` generates real services, builds them, starts them, and the agent can use them immediately. The agent can build new services on the fly.
It's definitely a core component of a bigger system. We are effectively trying to recreate intelligence and human life through models and robotics. So the key insights for me, the LLM is the cerebral cortex but we have a lot more to recreate. Once you map in sensory input continuously and give it physical robotics, things start to change. But even before that leaving these things in simulated realities is what will happen, and right now we have things that operate based on our commands, but a complete step function will be the things that act on their own and that will be a very dangerous time but also where we see some very surreal things happening. They might not necessarily be made in the same way either, they might operate on entirely different types of architecture.
We are now entering the closed loop game. Google doesn't need anyone else to accelerate their models. This is their bread and butter.
I'm both shocked but also not surprised that they continue to develop such efficiencies. Honestly it's like silicon and CPU architecture advancement. We kept shrinking it and shrinking it and it kept getting more and more powerful and here we are with AI and it's only going to be 100x more efficient with time. Maybe there's some point of decay but essentially the next 30 years will be more advanced than the last 30 and were going to be living in some sort of futurist blade runner scenario where gene editing is repairing ageing cells, organs and curing all sorts of cancers that haven't even appeared yet. Beyond our lifetimes people will live to 125 quite steadily and with great mobility and then obviously people will look to how do we get to living 1000 years, which of anyone is religious knows Noah and others lived to that age in a totally different era.
Anyway I'm going off on some tangent but look back 30 years. Now look forward 30 years. It's going to be insane. May God protect us.
Love how everyone boasted about replacing all the software with ChatGPT and then we end up with coding agents meaning the software engineer are STILL important. The sell is the development tool. It's classic cloud. Where did all the ops people go, many got subsumed by the cloud companies YET every company still has DevOps people to manage cloud infrastructure. The layer of abstraction went up but we still need the people to write the glue code and understand the business. OK great there's a new cash printer in the room. There's a new tool. Let's just start to ground the tooling in its new found gravity, profitability and IPO market dynamics... Reality has set in. The hype cycle is about to explode... Do you remember ride hailing and just how much cash was burned on credits pre Uber IPO. Then remember the IPO itself? These companies are not the new Google. They are a layer on top. Google was still the most efficient cash printing machine in history beyond the the US government and might still be. Will be interesting to see what the trillion dollar IPOs turn into. I'm going to say we see those prices get cut to a third in less than 5 years and scale back up over the next 15-20 years.
Every so often there is a trend and a hype cycle. It eventually dissipates. There's value in what gets built but it also becomes the silver bullet or the hammer used for everything. In 2-3 years it's going to die off, it becomes the norm technology trend but it's also part of a larger suite of foundational tooling, meaning so much of it is going to fade into the background and we're going to get back to good old problem solving. Doesn't mean we shouldn't learn and understand but yes we're all going to get burned out on AI chatter.