Just Tim

SaaS isn’t dying, it’s just reaching its final form. Software delivered as a service custom to your business - that’s where this is going. What we have called software as a service was really just remotely hosted software. Cloud software would be a better name for it. They just charged monthly for hosting it and called that the service.

You know how Dune is set after the Butlerian Jihad? In the original books Herbert is pretty clear it wasn’t the machines (AI) themselves that took over. People turned their thinking over to machines hoping it would free them, and that just let those that controlled the AI enslave them. The Jihad was as much against that “machine-attitude” (offloading judgment and decision-making) as against the machines. They banned anything artificial “in the likeness of a human mind,” (Basically they banned AI) which is why you get Mentats, spice-using Navigators, and the Bene Gesserit doing everything with drug enhanced wetware. What’s wild is he wrote this in 1965 — before many of us were born, before personal computers or anything we’d recognize as modern AI. And honestly I think Herbert’s version is more realistic than the “AI just takes over” story. The danger was always people using the tools to gain power over other people, not the tools independently deciding to rule. If someone wrote that premise today it’d feel like a direct response to the current AI discourse, but he did it decades earlier.

Yes. I went this direction with a fork that I later abandoned and it was really nice. Visual context management and skill/mcp pruning per project was really nice as well. So many of us have unorganized sprawl with these things

Prediction: Personal IT Audits and Consulting is a business that is going to start booming. So many people are sitting ducks with easy to crack passwords, unlocked credit, no 2fa and are going to be in pain the next few year.

IMO, marketing and GTM are harder. But if you want someone who cares as much as you do, you will need to offer equity. Since the product is already making 1m a month, you are not hiring a cofounder - you are hiring a head of product/engineering. For someone good it would likely be 20% and 150k+ salary.

If you get any more, I’d love to try it out.

Know what 50% of this even means and only have built 3. Am I cooked?

Kevin has earned my follow. A philosopher-poet of our time.

Someone give this man a platform.

Me too! 😅

I notice a lot of people are struggling to conceptualize Jev and where it fits in with current LLMs. In short its filling an important gap, not replacing LLM's 👇 It helps to look at how we think. When you open a support ticket, you don’t carefully reason through everything from scratch. You notice things immediately. The customer sounds angry. This looks like a billing problem. The request seems routine, but something about it needs a second look. You’ve made several judgments before you’ve decided what to say. Those judgments guide your attention. They let you move quickly through familiar situations and slow down when something needs thought. In LLM agents, we often ask the same model to do all of that: assess the situation, reason through it, choose an action, and write the response. Jev gives us a way to divide that work. Give it messy context and specific, typed questions, and it returns decisions, probabilities, and confidence in about 100ms. An agent can use those results to act on a routine case, bring in an LLM for deeper reasoning, or ask a human for help. Together, Jev and an LLM can form a system with something resembling the interplay between quick judgment and deliberate thought. The rough analogy is System 1 and System 2. Our thinking depends on both, and on knowing when a first impression deserves closer attention. That’s what makes the AGI argument interesting to me. We’re starting to build systems where different kinds of processing work together and help determine when each is needed. It’s still a loose comparison to human cognition. Fast decisions plus an LLM don’t establish general intelligence. But they give us a closer approximation of how we actually work: notice, judge, act, and think harder when the situation calls for it.

Funny, I'm about to implement something similar to fix the issue!

My experience as well. Im not sure where to place it in my workflow. teapaw.org/TimMacc/status/2097682…

I feel like for 3d and writing its great. Its really good when just prompting it back and forth, but on long running tasks with /goal its been horrible for me. teapaw.org/TimMacc/status/2097682…

to clarify - it only perfection spirals for me on long running tasks with /goal. Are you saying it does not do that for you?

Ive settled on something similar, but also: teapaw.org/TimMacc/status/2097682…

Astra sucks for long running /goal work. It gets in the weeds in a sort of perfectionist spiral and loses the big picture. Then it builds you a perfect "something" that's nothing like what you first set out for it to build. It's also really good at burning a $200 Codex plan in 24 hours doing these spirals. Still trying to figure out where it fits in my workflow. For now it needs HITL at gated steps to be useful. Anyone else hitting this, or is it just how I'm running it?