Easily my favorite spec driven development framework.
It scored really well in our internal evals as well.
I think it has the most sane ceremony and its model fits my mental model really well.
I've also been working on a TUI that will automatically generate "phases" with each one being a openspec spec.
I would highly recommend trying out SpecDriven development. I found it to be the most productive way to work with LLMs for larger tasks, and I have found that it improves performance on larger tasks.
To me, this is where LLMs should go. Collaborating on shared documents that serve as a contract that then gets evaluated post-implementation
I've made multiple attempts to write domain-specific languages for LLMs to use to guide software architecture so that I can have higher-quality software architecture and also so that it can communicate ideas to me in a more terse way.
One thing that I think LLMs are lacking right now is information density. I'm a guitarist, and I like this game called Rocksmith, but I think that its user interface kind of sucks. It's fun to play along with the songs, and it's fun that it scores me on the songs and gamifies playing guitar. For dense notes, the user interface just isn't very good.
That kind of made me think more about information density. A sheet of notes is very dense, but it takes a little more time to process. Guitar tablature is slightly less dense, but I think it strikes a better balance between treble clef and Rocksmith. Really, I'd rather have all three of those presented to me.
This is really where I'd like to go with how I'm writing software now. LLMs: I'd love to be able to just create a specification that is very dense and describes domain-driven design concepts to the LLM, and then have a workflow that will do adversarial review to evaluate those concepts after implementing a phase.
This also kind of solves part of the problem with design decisions and artifact storage and all those things that we kind of see LLMs scatter around a codebase. If it exists in the spec, then it can be referenced later, and you can document changes, etc. Also, if you do the spec right, it could be language-agnostic.
We no longer have the culture, the expertise, or the infrastructure to do these things. They moved it all overseas and to Mexico to save a quick buck. America is dead.
SpaceX has >11,000 satellites whipping around the planet. They increased the number of LEO sats by nearly one order of magnitude in bit more than 5 years.
So apparently, in the US, the culture, expertise and infrastructure do exist to do these things.
This is true for everything. They gutted the whole country. There is nothing left. Sold for parts. Collapse soon. That is why they are gearing up for total fascism, they know people are going to be pissed when the quality of life dies off for all of the US and there are no jobs.
This is what spec driven development tries to solve.
Multiple rounds of generating small contacts documents that grow from the original idea , trying to keep each slice small enough to process for a human to approve/disprove .
Eventually it leads to a long list of tasks grouped by functionality. You start a new context and the orchestrator agent dispatches tasks to sub agents with a limited amount of information provided to each sub agent.
Also should have adversarial review and approval gates with other agents and roles.
I have not seen any real life examples of successful application of SDD. I heard a lot of marketing BS, but nothing real. My own experiments with SDD produced very disappointing results even on very small projects.
I've had good results from SDD, and so have some of my teammates. The guidance I've heard over and over again is: the more you define, the better it does. I find that breaking things out into individual steps is helpful. However, your mileage may vary. Things like Gastown and GetShitDone, I have not found to be particularly useful.
Yes, you would think 'conservatives' would be big on conserving "god's creation", but no. Apparently having 'dominion' over nature means killing it, not looking after it.
Also, the disconnect between Jesus's politics and what the Christian Right practices is pretty jarring.
You two have put multiple constituencies in a small box so you can beat more people with a single stick. Even just in America, the only overlap between fundies, incels, and technolibertarians is the "R" they tick. Likewise, on the left, there's not much in common between labour activists and eco-hippies.
The problem is that companies tend to exaggerate their own scale and think they need k8s and dedicated infra people when they could get by with a handful of beefy VMs or dedicated servers.
I would take a kube cluster over a bunch of VMs I have to hand wire: wire releasing to, managing processes, restarting crashed processes, log aggregation, load balancing, networking, secret injection, cert management, DNS management, monitoring, etc... Any day of the week.
You just don't know what you're talking about, sorry. Kube is really easy now.
I ported my company over to k8s to solve a concurrency and scaling issues.
What 15 concepts? You're making me worry that I missed something. It was straight forward: pods, nodes, hw type, lifecycle, deployment. They run almost the same docker as the old ec2s used.
What did I miss? Is there something important I need to read?
Well, you're also describing Ardour (with the proviso that we don't allow scripts to much on the GUI side of things). Access to the "object model" from Lua is extremely wide-ranging, and since Ardour itself is open source, you can add whatever other access you need or want rather easily.
Easily my favorite spec driven development framework.
It scored really well in our internal evals as well.
I think it has the most sane ceremony and its model fits my mental model really well.
I've also been working on a TUI that will automatically generate "phases" with each one being a openspec spec.
I would highly recommend trying out SpecDriven development. I found it to be the most productive way to work with LLMs for larger tasks, and I have found that it improves performance on larger tasks.
To me, this is where LLMs should go. Collaborating on shared documents that serve as a contract that then gets evaluated post-implementation
I've made multiple attempts to write domain-specific languages for LLMs to use to guide software architecture so that I can have higher-quality software architecture and also so that it can communicate ideas to me in a more terse way.
One thing that I think LLMs are lacking right now is information density. I'm a guitarist, and I like this game called Rocksmith, but I think that its user interface kind of sucks. It's fun to play along with the songs, and it's fun that it scores me on the songs and gamifies playing guitar. For dense notes, the user interface just isn't very good.
That kind of made me think more about information density. A sheet of notes is very dense, but it takes a little more time to process. Guitar tablature is slightly less dense, but I think it strikes a better balance between treble clef and Rocksmith. Really, I'd rather have all three of those presented to me.
This is really where I'd like to go with how I'm writing software now. LLMs: I'd love to be able to just create a specification that is very dense and describes domain-driven design concepts to the LLM, and then have a workflow that will do adversarial review to evaluate those concepts after implementing a phase.
This also kind of solves part of the problem with design decisions and artifact storage and all those things that we kind of see LLMs scatter around a codebase. If it exists in the spec, then it can be referenced later, and you can document changes, etc. Also, if you do the spec right, it could be language-agnostic.
reply