Viewing profile — _fat_santa

I don't find the "AI will cause mass unemployment" argument compelling, in fact I see the opposite as being true. The reason we are talking so much about that now is that at the cu…

> Building a Saas product seems somewhat trivial at this point. The trap here is the word "seems". When I started building my SaaS years back I thought the problem space was trivia…

> If AI can build anything. Why do you need a human in the loop? I'm currently building a SaaS with my business partner. I'm the "tech guy" while he has decades of industry experie…

It's useful for running multiple long running tasks alongside your "primary" work. As an example I currently have 3 tabs open running a PR review, 1 tab running "autonomous develop…

At my org we've been building AI agents and one internal rule we have is to use at most 50% of the models context window with the recommendation to not go over 25% for large contex…

Another commenter posted the complaint: https://www.documentcloud.org/documents/28513012-samuel-tuni... The terrifying line of this for me is: "before and during the search", namel…

> The fundamental problem with the internet is that hosting sucks and no one wants to do it. It's thankless and it's expensive to maintain, both time and money. Apps are a way to n…

When me and my wife were purchasing our first home, we had everyone from mortgage people to realtors to our own friends and family that owned homes tell us to never use our home in…

What does the financial compensation need to be for an engineer to actually do this? I'm gonna assume that if you work at Apple and are being recruited by OpenAI, you are not a dum…

I see this case pretty simply. The states want to prove that Meta knew what it was doing to kids and did it anyways to raise engagement. Meanwhile it looks like Meta is trying to s…

I think what everyone underestimated was the absolute bonkers amount of compute it will take and how that compute must scale in order to keep up with larger and larger models.

I still use GPT-5.3-codex-spark which also runs on the Cerebras chips. Spark can run at >1000 tok/s but it's highly limited in it's context window size so it's not suitable many wo…

> If anything these models should be compelled to be public since they have been trained off public data I'm starting to come around to this idea TBH. For a while my position was: …

The US system is built to support entrepreneurship while the EU system broadly is to support the consumer and employee. The US will never be able to match the EU's consumer and emp…

IMHO I've never found the entire reasoning chain that particularly useful for my work. For me having a summary is honestly better from a context management perspective. I understan…

That's just fucking greedy. I've been working on a SaaS and it's honestly hard sometimes to not stoop to those greedy levels because the money is really there. Our policy is a subs…

There's a similar project for Codex Desktop: https://github.com/ilysenko/codex-desktop-linux . After going through this process to get codex installed on Linux I'm honestly baffled…

At my company we're using Claude Code w/ API Billing and I found that unless you're running ralph loops on Opus with extended thinking, it's very hard to blow through more than $20…

I've toyed around with worktrees but haven't found them very useful beyond that. I generally find it much easier to carefully prompt an agent so $TASK1 does not interfere with $TAS…

I'm on OpenAI's Pro (200/mo) plan.

I wonder how much of Uber blowing their AI budget and MSFT pulling their claude code licenses can be attributed to "tokenmaxxing". When Meta announced token leaderboards and other …

Their open weight on device models are really impressive. Partly because I think they are the only ones out of all the frontier labs even working on local models.

The biggest issue I see with discourse around AI is you have two voices: one is of the tech CEO's and other elites that talk about it largely in the abstract and how it's going to …

I feel like the way many companies implement AI right now is very very wasteful. For context I'm looking into adding some AI elements to my SaaS app and I'm looking at running on-d…

One distinction the author didn't make was personal sites vs product / services sites. My personal site is for me, but the site for my SaaS app? That's for my customers.