Hello from assembly programmers to present day javascript folks. Joke aside, I sometimes think how VS Code is written in such layers and layers of code - ~200mb of minified code - Java based IDEs were worser with almost 1GB of code (libs/dependencies). And VS Code did beat native editors (Sublime) of its time to dominate now - may be because of the business model (open & free vs freemium). But it does the job quite well IMO. And it enabled swarms of startups to go to market including billion $ wrappers - including Cursor, Antigravity and almost all UI coding agents. I remember backend developers (Java/C++ type) looking down upon Javascript developers as if we are from an inferior planet or something.
How many of us remember that VSCode is actually a browser wrapped inside a native frame?
Thought so until saw this. Man, he is the co-founder of Github and already seed-funded. How can someone refuse him? 17M is a small amount considering the valuation VS Code Agent wrappers are getting
wish they enable the actual iphone 16 with a full-fledged OS that we can plug into an external monitor.. I think samsung tried it but didn't get mass appeal. Apple could do that IMO - would have even avoided launching neo as students own a device in the form of phone or tab anyway..
If the management is the one actually paying for the software from their own pocket (founder), the tables turn. There are millions of SME owners who are forced to pay for B2B software just out of necessity and not having resources to build it in-house.
What are you implying?. He would have had to hire a good developer at least for a full month salary to build something like this.
And if you are thinking enterprise, it would take 2-3 developers, 2 analysts, 2 testers, 1 lead and 1 manager 2-3 months to push something like this. (Otherwise why would lead banks spent billions and billions for IT development every year? What tangible difference you see in their website/services?)
5000 calculators may look excessive, but in this case it magnifies the AI capabilities in the future - both in terms of quality and quantity.
Scary is that the LLM might have been trained on the entire open source code ever produced - which is far beyond human comprehension - and with ever growing capability (bigger context window, more training) my gut feeling is that, it would exceed human capability in programming pretty soon. Considering 2025 was the ground breaking year for agents, can't stop imagine what would happen when it iterates in the next couple of years. I think it would evolve to be like Chess playing engines that consistently beat top Chess players in the world!
>Most modern backend is building consistent distributed state machines, you need to cover all the edge cases, deal with concurrency, different clients/contracts etc. I would say getting BE right (beyond simple CRUD) is going to be hard for LLM simply because the context is usually wider and hard to compress/isolate.
Seeing the kind of complexity that agents (not standalone llm) are able to navigate - I can only start to believe - just a matter of time it can do all kinds of programming, including state of the art backend programming - even writing a database on its own - good thing with backend is its easily testable and if there is documentation that a developer can read and comprehend - an llm/agent would be able to do that - not very far from today.
>Isn’t frontend more complex? If my task starts with a Figma UI design, how well does a code agent do at generating working code that looks right, and iterate on it (presuming some browser MCP)? Some automated tests seem enough for an genetic loop on backend.
Haven't tried a Figma design, but i built an internal tool entirely via instructions to agent. The kind of work I could easily quote 3 weeks previously.
I disagree - having worked on backends most of the time, I find modern frontend much more complex (and difficult to test) than pure backend. When I say modern frontend - its mostly React, state management like Redux, Zustand, Router framework like React Router, a CSS framework like Tailwind and component framework like Shadcn. Not to mention different versions of React, different ways of managing state, animation/transitions etc. And on top of that the ever increasing complex quirks in the codebase still needed to be compatible with all the modern browsers and device sizes/orientation out there.
I used to think the same until latest agents started adding perfectly fine features to a large existing react app with just basic input (in English) . Most of the jobs require levels of intelligence below that. It's just a matter of time before agents get to that.
Wondering why someone did not solve the problem already? Of all the countries in the world US is brimming with entrepreneurs who want to "solve" a consumer problem, and with modern population I assume there is enough demand on fresh/healthier products - why on earth someone wouldn't try to fix it there?
The openai agent builder launched 2 days ago is basically inspired by n8n. n8n when launched wasn't an AI tool, it was inspired from numerous enterprise integration tools like Mulesoft, which were inspired by dozens of other enterprise tools, some launched even decades ago.
If you haven't tried you should check it out. Its an amazing way for no-coders to build something substantial in a relatively quick manner.
We replaced Slack with Mattermost for one of the teams - and guess what we don't miss Slack there. Threads, push notifications everything works fine and you get more features at least compared to the free version of Slack
But Americans can hope for a regime (policy) change every few years though. You could argue both the political ideologies are broadly doing the same shit, but you can hope or lobby for change. On the other hand, imagine your unfavourite politician/ideology remaining in power for the eternity!
How many of us remember that VSCode is actually a browser wrapped inside a native frame?