Hacker News: erikus

New comment by erikus in "F-Droid 2.0"

erikus — Thu, 24 Sep 2026 21:00:18 +0000

I wasn't sure if this was a joke about Android being unintuitive so I was sad to see that enabling high quality line breaks is indeed something you have to configure:

https://developer.android.com/develop/ui/compose/text/style-...

New comment by erikus in "Ask HN: Who is using MCP in production?"

erikus — Fri, 04 Sep 2026 13:13:55 +0000

I use MCP for a voice assistant as well.

I got a Pebble Index 01 ring and it has support for custom MCP servers. I run one on Tailscale and it can interact with Home Assistant, my home issue tracker, my Anki setup, etc.

I've come full circle on MCP. With agents with a shell tool they quickly became unnecessary but these days I've been coming up with more agentic use cases where I don't want to give the agent a shell, and a narrower MCP interface is a great fit.

New comment by erikus in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

erikus — Sun, 12 Jul 2026 20:14:09 +0000

Ah, thanks. It's been hard to plan around these last-minute changes. I rushed to implementation on a spec I should have spent more time on because of the looming deadline.

New comment by erikus in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

erikus — Sun, 12 Jul 2026 20:04:06 +0000

I use both now and agree they're basically interchangeable.

I appreciate that Codex is open source and OpenAI has explicitly said using the subscription with other agents is ok. OpenAI has been much more consumer-friendly recently.

New comment by erikus in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

erikus — Sun, 12 Jul 2026 19:55:03 +0000

For me as well, at least this month to use more of Fable. We'll see if they extend Fable access because of people like me.

New comment by erikus in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

erikus — Sun, 12 Jul 2026 19:52:03 +0000

I'm pretty sure the system instructions are a function of your environment and not the same universally. That said, there should be a finite number of branches so still cacheable.

New comment by erikus in "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second"

erikus — Mon, 08 Jun 2026 23:13:18 +0000

I'm amazed at how steep the AI learning curve continues to be and how people are spread so far apart on it. I think supercharged learning with AI and agents is undervalued at this point but that more people will realize its utility over time, especially as a complement to delegating work.

It also makes me think about the temptation to stop thinking with these tools, i.e. "cognitive surrender". Addy Osmani wrote a nice blog post about this: https://addyosmani.com/blog/cognitive-surrender

New comment by erikus in "MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second"

erikus — Mon, 08 Jun 2026 23:01:36 +0000

Agents completing work faster would certainly help me as well since I also find context switching exhausting above some threshold.

Build and test would move back into the critical path, though, and for some projects that will take effort to bring down.

New comment by erikus in "North Korea's computer operating system mirrors its political one"

erikus — Mon, 28 Dec 2015 06:14:04 +0000

Direct link so others don't have to look them up: https://www.facebook.com/photo.php?fbid=10151143106612055&se...

New comment by erikus in "Former Apple Exec goes to JC Penney and slashes prices by 40%"

erikus — Sat, 28 Jan 2012 18:52:07 +0000

It's actually 0.05% more for a $20 item, and if we estimate that $20 is the average price of all items it isn't very significant.

New comment by erikus in "Is Foursquare in trouble?"

erikus — Wed, 04 Jan 2012 17:44:50 +0000

I was able to get a couple of specials honored in SF (buy one get one drinks in both cases).

Recently I've seem some of the specials requiring an AMEX credit card linked to my foursquare account, which I feel crosses the "worth it" line.