brandensilva

I am looking forward to seeing it!

It feels bad because I know your team was working so hard pre AI to make state machines more accessible and bring such a powerful concept to the world.

I know it didn't pan out exactly, but I really want durable execution state machines that exceed workflows one day.

I keep thinking to myself can I enforce my AI layer to have some deterministic durable state machine running it and I'm not deep enough on them from a creator/author perspective to answer that question like you, but keep us posted on the changes.

Yeah its bothered me that workflows get all the limelight while state machines are more than capable. They just need durable execution for state charts. I think Cloudflare was going down the durable object actor model for a bit, but not sure if they abandoned that coded project.

I've been wanting to code up an AI flavor wrapper around state machines that will be visible as an AI generated image in PRs.

I often have my AI code output one just to make sure my logic feels more sound. Along with mermaid charts if I need to toy around or drop into stately for more power.

I've always been a fan of state machines and have hoped for their adoption to grow.

Having visual understanding of state is becoming increasingly important for AI generated code you don't nearly understand as well as the human variety.

It seems many still favor store based reactivity state in frontend frameworks.

I contribute to it being the default so why change and because libraries like xstate are far more difficult to learn the syntax and are more verbose. But with AI that's hardly an issue, so I wonder if there is more to it I don't see and we just haven't seen the state chart reach it's peak yet.

Also curious about this, it seems like it would be important to guide these tools more specifically based on the domain of expertise.

The sentient had already sailed. It's hard to trust Anthropic here given the ringer they have dragged us through.

Contrast that to what GitHub did which was to pause new customers to ensure quality remained and things were stable.

We are at the point where uncontrolled capitalism collides with humanity.

I do wonder where we go from here.

Yup it's based off their playground so plaything is the right word.

It's a wrapper around that. I definitely appreciate the better design output from Claude code but it has a ways to go before it can replace serious design contenders.

Anthropic is burning their good will faster than the tokens we use these days. It is hard to be excited about these new features when the core product has been neutered into oblivion.

I'm glad I'm not the only one that feels this way. I've been creating a local first open source piece of software that lets me spin up different agent harnesses with different runtimes. I call it Major Tom because I wanted to be set free from the imprisonment of Claude Code after their DMCA aggression for their own leak and actions leading to lock down from open source adoption.

Don't put all your eggs in one basket has be true for me and my business for ages.

I could really use the open source community to help make this a reality so I'll release this soon hopefully to positive reception from others who want a similar path forward.

That's the thing though. Where do you draw the line from the hitman and the one who ordered it legally in their official capacity.

I've been thinking about this a lot about what are the benefits of UI, GUI, TUIs in the wake of AI.

I've come to the thought that we built interfaces honed to the way we visualize and work. We simplified many things down to just clicks. A really good UI captures intent and use very well. It doesn't require constant written language input when one mouse click is enough. Also it appeals to the aesthetic experience too in some ways to enhance the brand.

Design might be subjective but that's a good thing to act as a differentiator for companies.

Too many people assume pretty or nice looking is what design is. It's a very empty statement that disguises how important design works to make our lives easy.

Yup, even without multiple users I took an open source speed reading app and quickly found myself a month deep in features just to expose it to multiple integrations for maximum accessibility. OAuth, MCP, CLI, API keys, secure and rate limited endpoints for content ingestion, parsing engine, a nice CI/CD pipeline that builds cross platform, a marketing site and it just kept going.

It was a test to see how much work was involved and what vibe coding felt like in one month. I plan on releasing it soon because I feel like it is the best speed reading app available but man it's a lot of work for even what seem like simple cases.

I'd be worried for anyone touching what I did if they did not have experience doing this.

They found luck and success and continue to compound that. However it's easy to make so much money when you have that much already. Just promise the world or invest in companies that do and ride unicorns with private investments into the sunset. The risk they take now is very low.

I feel like they will never suffer the consequences of their actions in any negative way should they get it wrong.

Rarely do we see billionaires not become billionaires because they know how the game is played because they shaped the game so they only ever fail upwards.

ccleaks.com seems to be "temporarily paused" from Vercel.

Here is another one that goes in depth as well: www.markdown.engineering for anyone going deep on learning.

Even the prompt history is notoriously weak given how little Claude Code and some of the others display to give developers confidence in the process.

There needs to me more design rep indeed.

On top of that, Palantir has been designated as a multi year contract and they use Anthropic under the hood.

I think people are having a hard time figuring out use cases so yeah the AI is the most exciting part.

Ultimately the conclusion will be humans are the bottleneck somewhere along the path and no amount of agents will replace that person because you don't run businesses on vibes and code.

Propaganda state run networks are for dictatorships, not democracies.

Man the perf changes for this version are awesome. Thanks Vite.

I'm finding it in some cases I'm dealing with even more code given how much code AI outputs. So yeah, for some tasks I find myself extremely fast but for others I find myself spending ungodly amounts of time reviewing the code I never wrote to make sure it doesn't destroy the project from unforseen convincing slop.

Even banks are backing out of AI data centers as the risk is too great. Tells you right away that they know the risk exceeds even their willingness to finance the wealthiest ambitions.

We can go all the way back to the Patriot Act honestly. All admins have perpetuated this. Trump is just end game.

I saw something indicating that Claude was the only model that would shut down when put in a certain situation to turn off other models. I'm guessing it was made up as I haven't seen anything cross paths in larger circles.

I'm afraid that all the foxes are in the chicken coop at this point. Which is a nice way to say we're probably hosed until the people rise up and force change.

It does seem like Anthropic is at least the only big AI company that is pursuing some safety discussions around their technology like not using it for surveillance and war for killing people autonomously.

This administration is wielding a power that was meant to serve Americans in the past by forcing companies to conform to an agenda that is anti-democratic/freedom/constitutional.

I'm just not confident they will stand against this administration when the going gets tough but let's see what happens this Friday I guess.

We might be witnessing some survivor bias here based on our own human conditioning. Successful PRs aren't going to make the news like the bad ones do.

With that said, we are all dealing with AI still convincingly writing code that doesn't work despite passing tests or introducing hard to find bugs. It will be some time until we iron that out fully for more reliable output I suspect.

Unfortunately we won't be able to stop humans thinking they are software engineers when they are not now that the abstraction language is the human language so guarding from spam will be more important than ever.

I totally feel this. Prior I never had time for doing this but now I just do it without even thinking about contributing.

When laws no longer serve the people and you have a lawless government doing whatever it wants, they are merely strongly worded suggestions. We give laws their power so I don't think this government realizes just how poorly things look with the DOJ now and how little trust there is for anything coming out of the federal government.

Honestly does show how the industry has failed to bring simple things like localized cron and scheduling to personal compute too.

These things seem powerful when you can schedule reoccurring scripts l but it never was easily accessible to the masses.