rpunkfu

Exactly, it’s about knowing how to use it at this point.

We achieved this with opus 4.6 last year, what those providers give you is great front end on top of it, which allows users to delegate even greater part of their process to model.

Open Weight models have already reached level at which you can do a lot of productive work with them. They really don’t have to keep beating newer and newer models, of course it’s great for them to do things cheaper and faster, but we’re already past point where open models have to “catch up”

Wait until you take a look at X. People from Vercel / CloudFlare can essentially build todo list and get funding

Audit logs being behind-paid-plan feature is crazy.

I was talking about it for a while with colleagues. AI besides other benefits, needs to be treated as great interface for discovery, you have your features baked in, AI uses it via your users and MCP, then you figure out what are actual flows of my users and then you build it

Yes, exactly why I'm making that (potentially harsh) statement.

It really shouldn't take much more than that, most of what you see there is already pre-loaded on disk (I'd hope) like your most recent plays etc, much of it can be cached and rendered directly from that cache, even progressive loading of store images should make it a very, very tiny download from the web.

That should've loaded instantly.

App to launch apps is loading in little over 5s, on what I assume is high-end gaming pc.

Truly something to be proud of..

AI iterate quickly, with 100s of followups to fix results

I’ll have to update the blog post, since API and capabilities of ctx grew a lot but one of examples here explain for we’re doing it.

https://ctx.company/blog/introducing-ctx-traits/

They can fill random document as well, it’s their expertise which template to use that fills your scenario and additionally once it gets to subtle nuances, you don’t want to do those yourself either.

It’s not what people are looking for, but what they wrongly claim.

I don’t think it’s about telling agent what to do with skills for most part anymore as well.

Problem is not having to remember to run agents in exact sequence and not having to repeat the processes.

That’s why I’ve created ctx traits and using them everyday, biggest wins for me are: sync across repos using git-based dependency manager and validator, which ensures version of the process / knowledge I’m using has been approved by me and hasn’t moved without my approval (similar to dependency managers lockfile approach).

This has allowed me to use same traits (it’s extension of skills with typed schemas and procedures, you can use skills with it as well as usual) across different repos without any copy pasting etc.

There are additional cool things like type-driven procedures with specific harness/agent associations and many more cool things coming soon.

Contributors: Cursor Agent

I believe that “it’s about the harness” captures an important idea, but I also think it’s helpful to consider the harness and the procedure separately.

The harness provides the model with its tools, context, and environment for execution.

However, I prefer not to have the model within that harness also bear the responsibility for remembering the process steps—like plan, implement, review, fix, and verify—deciding when to move from one to the next, and keeping track of the loop's state.

For tasks that need to be repeated, I’ve been moving that part into a reliable, deterministic runtime. Inside it, Claude, Codex etc simply take on interchangeable roles.

This setup makes changing models much simpler: the overall process remains consistent, and each role can be optimized independently.

I’ve been developing this approach as ctx.traits, if you're interested, here are the docs: https://ctx.company/traits/docs/quickstart/example/

I think you might be interested in what I’m working on:

https://ctx.company/blog/introducing-ctx-traits/

Yes, in this case mcp or cli or even skill is better, you can ask agent

It sounds like whining for the sake of it really.

Reach

This is exactly what I’ve been building with ctx.traits :)

https://ctx.company/traits/docs/

Absolute cinema. OpenAI writing “100 reasons why it’s not my fault” post.

Would’ve been great to be able to lock/sync orientations on both

Author here.

For months, I have been searching for an approach to agents that does not feel like negotiating with the model. Each pattern I tried arrived with a long list of requirements and an implicit expectation that I would overlook its shortcomings, and left me managing output at several layers, always with a sense that I was compensating for something the system should have handled itself.

I eventually settled on ctx.traits: agent behaviors and workflows expressed as typed modules. Rather than writing in prose Markdown, you author in TypeScript. This produces a specification file, which becomes the artifact that is reviewed, locked, and diffed. The runtime executes the procedure one frame at a time: at each step, only the declared inputs are provided, nothing more. Submitted output is validated against the step's schema before it is accepted. The loop exits on a typed verdict field, not when the model arbitrarily decides it is finished.

If you have thoughts, questions, or experiences with similar patterns, I would appreciate hearing them. I am still refining this approach, and outside perspectives are valuable.

You’re not, thing that makes it agent friendly is copy path button

Ironically from my experience seeing AI code a lot, it probably follows his clean code verbosity beautifully

It doesn’t matter which domain it is, AI should be utilized at anomaly / patterns detection and prototyping, with goal of a prototype to become coded as discovered pathway.

I don’t understand why companies still place AI in their system at authority-forming level, if anything it should sit at least behind single guard / validator that is explicitly coded and tested, never in front of presentation layer.

tldr: greed

Yet again another product that could’ve used AI to help with a problem but basically puts everything in AI hands and calls a day.

AI is great for learning, but you know what’s most important thing for children as part of their learning? Presence of a parent.

Why not make this an assistant for parent & child learning session, where you can use it as encyclopedia lookup or permutation / generation of an exercise or even cheatsheet / checklist for your learning session?

I think there’s huge value in being able to have such thing, where you don’t have to pull out your phone when doing something with your child and instead you could ask that assistant for a lookup online, but putting child in front of a screen and putting it’s self-development in a hands of AI is just irresponsible, lazy and quite frankly dangerous