Hacker Newsnew | past | comments | ask | show | jobs | submit | Myrmornis's commentslogin

> the worst case scenario for a rebase gone wrong is that you delete your local clone and start over. That’s it. Your remote fork still exists.

This is absolute nonsense. You commit your work, and make a "backup" branch pointing at the same commit as your branch. The worst case is you reset back to your backup.


The article focused on the local stdio MCP tools used by coding / computer automation agents like claude code and cursor, but missed the fact that we will need protocols for AI agents to call networked services, including async interactions with long-running operations.

Yes, it reduced the author's credibility; it seems that whatever the accuracy is of some is their MCP criticism, they just like criticizing things.

Any recommendations for a talk by him to watch or something written by him to read?

yes

on a serious note, this recent-ish interview on AI is illuminating https://www.youtube.com/watch?v=dq8MhTFCs80


In particular, and speaking as a backend engineer with zero web design skills, building things with charts/graphs is amazing nowadays! You can literally just operate at the level of "add another line representing the foo data", "add a scatterplot below it", "make them line up", "actually, make it a more reddish pink" etc. In the past I've had opinions about d3 and vega-lite and altair and matplotlib etc and learned how to use those ones at a superficial level at least. In my last personal UI with charts I didn't even ask it what framework it had chosen (chart.js is the answer)

Not saying you were suggesting it but people committing AGENTS.md in shared repos is pretty annoying IMO. Those things are personal.


Touch-typing. In some countries it's common to learn this at school as a teenager but that's not true of all countries. With LLMs this skill has become significantly more important to programmers.


Speaking of, are there resources for people who type fast but want to get competitive, ie into the top 20 on typeracer for example? Beyond "just" practicing.

Any suggestions would be appreciated!


That's not how LLMs work. There are several sources covering the basics nowadays!


Can anyone give any tips for getting something that runs fairly fast under ollama? It doesn't have to be very intelligent.

When I tried gpt-oss and qwen using ollama on an M2 Mac the main problem was that they were extremely slow. But I did have a need for a free local model.


How much ram are you running with? Qwen3 and gpt-oss:20b punch a good bit above their weight. Personally use it for small agents.


Use llama.cpp? I get 250 toks/sec on gpt-oss using a 4090, not sure about the mac speeds


“This is a very advanced technology, and whatever nation masters it first is going to have an incredible advantage,” Loureiro says.

https://energy.mit.edu/news/funding-the-fusion-revolution/


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: