Location: Florida, USA

Remote: Yes

Willing to relocate: Yes

Keyword bingo: C++, C, Python, JavaScript, TypeScript, SQL, Docker, AWS, Terraform, nginx, QEMU, Modal, perf, BPF, React, Next.js, Node.js, FastAPI, Redis, NoSQL

Resume: https://medbar.dev/resume

Email: dsantamaria1245@gmail.com

Looking for Full Stack, Systems, founding engineer, or freelance/contract roles. I have experience with YC-backed startups, interned at Google, and I'm comfortable across the stack from applications to metal. I have a background in competitive programming and math and spend most of my free time reading technical topics and working on projects that interest me, which usually falls into systems engineering, distributed systems, or AI engineering.

You can book a short call with me through here: https://calendly.com/dsanta01

Skiplist operations are local for the most part, which makes it easier to write thread-safe code for than b-trees in practice. Anecdotally, they were a nice implementation problem for my Java class in uni. But I liked working with b-lists more.

Skip trees/graphs sound interesting, but I can't think of any use case for them off the top of my head.

OP is about a German learning class, so yes, there is a point. AI improving will not learn you a language faster than immersing in it until, I suppose, neural links become mainstream.

Where are these ‘3-story high’ equations you speak of? The most work I see in the article is 3 lines long.

> The classroom should be about using AI better not ignoring it.

No, it shouldn’t. I’m not bearish on AI but it shouldn’t replace any part of a classroom where the objective is to learn and communicate in a new language (German). The typewriter argument is memorable and interesting - the article points out the lack of editing forces kids to slow down and think about their writing, as well as iterate through multiple drafts. It’s not a nostalgia thing, they’re not old enough to have ever used one before.

I could see an argument for adding on a new class for GenAI, agents, context engineering or what have you, but considering how behind current US curriculums already are and how quickly the AI field moves, I can only see this ending in wasted time and money: even an up to date class will be stale by the time it’s over. Kids will end up learning this anyway outside of the classroom, no use lecturing them on something they’ll already know.

I completely disagree with you.

You can do all the same learning with AI tools, with the added benefit of developing extra skills on top.

This notion that AI automatically reduces learning seems more born out of fear than reality. There are also different kinds of learning.

People who really want to can still go back to typewriters. Forcing it into a mandatory curriculum though is a step backwards. Just like it would have been pre AI.

For anyone interested and with 30 minutes to spare, I would recommend the youtube video [1] by Reducible for an intuition on how FFT works.

[1]: https://youtu.be/h7apO7q16V0

Adding a scheduler to my hobby kernel with the goal of a full shell coming soon, and an inference engine from scratch in C++. It's been fun.

No.

I still use vanilla Claude Code without MCP or skills, am I in the minority? Not trying to be a luddite.

Skills and MCP are useful for when you need to repeat specific processes, perpetually. Without them the task description and reasoning falls out of the context window, or is compressed, and the process fails.

An agent will eventually forget, or hallucinate, guardrails and requirements. Yes to AGENTS.md, but when you're actively managing the whole context window in a long-running task you don't want to just keep jamming stuff in there and hope for the best. Skills help budget tokens and stabilize around specific outcomes.

If your use case is not agentic, as you build a skill corpus you can begin having the model reason at higher and higher levels about the outcomes you're aiming at.

Eg: I'm super lazy now and ask Claude to launch the project instead of just running the command myself. This is probably best done as a skill.

AGENTS.md doesn't fall out of the context window so you just put whatever commands you use in there. Every time it gets too big you rewrite it.

Never had an issue doing this

How long have you had an agent performing the same task, or trying to improve performance towards the same outcome?

I’m not really talking about coding. I’m talking about autonomy.

All day every day is the answer.

Me too just use AGENTS.md and it seems to work. I don't understand what problem MCP is trying to solve and skills just sounds like something you can do in AGENTS.md

What am I missing out on?

Repeatability (see my response to op).

I would guess the top 10% of actual performers do the same - the people who talk about harnesses and chain multiple systems together etc will be mid table somewhere

Bookmarked! Awesome, thanks.