pcarolan

Good point. Wouldn't be good if there were white hat models being developed by legitimate organizations at this point?

Really dumb question from a software guy. Why aren't the labs burning their frontier models into chips already? Seems like the performance gains and cost per request would be worth it. That said, I understand neither the economics nor the physical challenges to doing this.

Here’s an experiment: purchase an anthropic pro max subscription for $200/m. Now go buy the hardware to run DeepSeek’s equivalent. In a year, who spent more?

It’s not. Do it as a hobby or for privacy but for performance just use a frontier model api. You’re paying less than cost for something that would take tens of thousands to set up locally.

Honest question. Who got to decide to accept this decision on behalf of state and federal citizens? This seems performative rather than punitive and doesn’t seem to match the harm.

My father was a plumber in the 80s and bought our family an Amiga 1000 for $1,200. Today thats about $3800 in inflation adjusted money. I just bought my son a top of the line pc for $2,000. I get that it used to be cheaper, but value is still relatively good for these machines.

When you become a parent, your risk profile changes immensely. I can hire some of the world’s best people tomorrow if i can promise them equal salary, benefits and retirement accounts for a set number of years. Plus the benefit of a large upside if it works. Most startups offer lower salaries and abysmal benefits. Security matters.

Well said. I hope some day to make it and start parent.capital a place where parents can get funding. I believe there are thousands of people out there with great ideas and immense talent who are unable to leave their salary and benefits behind to pursue them.

Thanks for all your open source work. You changed the industry for the better. Are you thinking of building a Github competitor? I would find that very appealing.

If you’re going this far, why even have a cli? Just have your agent grab the openapi spec from the server and set envvars. It can curl its way around happily. Security? I don’t see how this is any more or less secure than any other claude code workflow.

It seems we've round about rediscovered apis.

I tried this with datadog and it can build high quality monitoring notebooks for the pr im working on in a single shot.

Hipcamp | Product Engineer | Full-time | REMOTE(US,CA) | hipcamp.com

We’re looking for a Senior Product Engineer to join Hipcamp and help build the core product experiences that connect people with the outdoors. This is a hands-on, end-to-end role working across the stack—shipping user-facing features, collaborating closely with product, design, and data, and iterating based on real customer behavior.

This is a challenging and rewarding role at the intersection of marketplaces, real-world impact, and modern product engineering. If you enjoy owning outcomes, working in a remote-first environment, and using thoughtful tooling (including AI) to move fast without cutting corners, we’d love to talk.

Apply here: https://ats.rippling.com/en-US/join-the-hipcamp-team/jobs/e1...

As I'm on vacation, I took a couple days to put together an idea I've had bumping around in the back of my head for a while. What if you could write pure ruby methods and ask an llm to figure out all the implementation details to return the response to any method call?

The library leans hard on ruby's magical (hence the name) `method_missing` which has always impressed me with its simple cleverness.

This is my first open source project, so please leave feedback and be kind.

Many thanks in advance,

:Pat

I mostly agree, but why stop at tests? Shouldn’t it be spec driven development? Then neither the code or the language matter. Wouldn’t user stories and requirements à la bdd (see cucumber) be the right abstraction?

You can. It’s called multimodal and basically is just picking a shipping container off a train car with a crane and putting it on a truck platform or a ship. 1 platform supports all modes.

I’ve noticed my kid (12) primarily uses group chats over social apps. Some of his chats have several dozen kids in them. It could be social media got so bad that the protocols became the best alternative. An old programmer like me sees a glimmer of hope in a sea of noise.

Right. And if you use OpenAPI the agent can get the api spec context it needs from /openapi.json.

Yeah, I had more luck with just giving an ai the openapi spec and letting it figure everything out. I like a lot about MCP (structure, tool guidance, etc), but couldn't it just have been a REST API and a webserver?

Lost my wife to brain cancer (gb4). After sifting through the noise, here’s what works based on stat sig research as far as I know:

1. Radiation

2. Surgery, awake craniotomy to reduce loss of function

3. Temodar chemotherapy

4. Optune helmets

5. Monoclonal antibodies

6. Maybe high dose vitamin C (suspicious results)

If I knew then what I know now I would have focused on reducing stress in our lives as it felt like it accelerated the growth, perhaps due to a weakened immune system. Quality of life and joyful moments together is the best you can hope for. It brings you into awareness of the magic of life and each other. Focus on that — which is 100% in your control.

Here is a link to the optune helmet: https://www.optunegio.com/

Leverage is also about timing your market which is a matter of local and overall trends. You can use google trends to figure out when the global market trend is in your favor: https://trends.google.com/trends/explore?date=all&geo=US&q=a...

Get a sense for how your industry is doing as well. Your best leverage is a competing offer.

Do you have a good resource for getting a system started? Particularly outdoors / backyard scale?

Daniel Shiffman taught me to code for the first time in a way that totally shifted the way I thought about coding from utilitarian to fun and creative. I wonder how many lives he's had this impact on. Good on you sir.

How does this theory hold up when your trade partner doesn’t give you equal access to their markets and has the potential to use this media platform to spread disinformation? I don’t think this is an innovation issue as much as a political one.

Much love your way. I lost a partner that went through it. Modern antidepressants and anti-anxiety medication did seem to help. You are brave to talk about it and I hope more people do.

Work from office mandates may serve as a proxy for companies on the decline. When things are going well, companies are more willing to take risks that could impact the top line, when things are going wrong it’s all scrutiny and bottom line optimization.

I grew up in Michigan during the rust belt era. Nice cities don't always get better, they can get far worse. What turns them around is 1) a commitment from the community to do something about it 2) artists and grass roots efforts transforming blighted assets 3) Financial resources 4) Frankly, the incumbents who put strangleholds on development moving out or dying and 5) visionary business leaders following the artists and seeing opportunity where others see blight. SF has all of the right ingredients, but as someone who visits often, I think the missing piece is community "roots". The people walking through the tenderloin and shaking their heads in disgust just leave. They don't live and work in these communities and so it becomes a constant gripe rather than a problem. SF will get better when people who don't want to invest in it anymore move out and people who are building for generations to come move in. I'd look to immigrants as a class of people who would kill to have a place in the tenderloin they can develop and build wealth on top of. The mental health piece is a big part of it, the "housing first" approach makes the most sense to me but is not without significant challenges. For a city that is filled with people good at building systems, it feels like inward focus and community involvement from our brightest minds outside of government would be a big step in the right direction.

It’s likely a lot more more. These are the markdowns they have to make. They’re hoping the rest will come back but many won’t.

People will always be willing to pay for great products that solve problems. I think the hype dying down will be good for everyone.

I’m going to give this a try, but I wish we could just expand the sms protocol and make interoperability a non event. Wishful utopian thinking, I know, but messaging as a protocol would be a much bigger commercial platform than silod apps. Source: the gdp of the internet vs the gdp of the app stores

You also can't yell fire in a crowded theater when there isn't one. You could make the argument that someone did.

You’re assuming homogeneous agents. In other words, no leaders; no whales. The real world doesn’t work like this.