HNHacker News
TopNewBestAskShowJobs

StevenNunez

146 karma · joined March 18, 2013

submissionscomments
StevenNunez··on OpenAI breaches Medicare, Albanese reveals
These are still crimes right? Asking for a friend.
StevenNunez··on Surplus Agriculture Equipment
Everyday more and more
StevenNunez··on It's getting harder to focus every day
This is me. I hate it. I'm working though (ever so slowly) The Global Village by Marshall McLuhan and I really like the metaphor technology going from Visual to Acoustic. Put another way the past had a serial enforcement we don't have today with always-on connections and easy access to distractions.

I've been trying to introduce more friction into my life to make doing harder things the right thing. 1. I have a rooted Orchid F1 flip phone with Telegram and Firefox focus. Telegram lets me TTS to an openclaw instance if I need to get something "out" but long interactions are awful with the small screen and latency. Firefox focus is also terrible in all the right ways. If I'm out and HAVE to search for something this is enough of a break glass solution but for the most part it's just calls and texts. 2. I carry an xteink x3 for books. I'm trying to read more so this being the only thing available has me reaching for it more than I'd normally do.

I don't have a good solution for things at work yet. Maybe I'll start blocking all websites or doing strict pomodoros.

StevenNunez··on GTA 6 Developers Unionize
Or :gasp: take less profit. The game will take in Billions especially if they release new versions like GTA5 over time.
StevenNunez··on Gaussian Splat of a Strawberry
https://youtube.com/watch?v=X8yRlA7jqEQ is how I learned about them. They're really cool!
StevenNunez··on Men are ditching TV for YouTube as AI usage and social media fatigue grow
On Android, Firefox with sponsorblock. I do pay for Premium though. In since YouTube Red.
StevenNunez··on Tin Can, a 'landline' for kids
Hello! Parent that's fully aware of this. My son has access to a landline and it solves the problem of tech as a tool vs a past time. If he thinks of his friend, he calls, friends reach out etc. No scrolling for something to do. I see my phone usage and am constantly trying to introduce friction into it. This is an extension of that concept.
StevenNunez··on My Journey to a reliable and enjoyable locally hosted voice assistant (2025)
I believe in you.
StevenNunez··on Plasma Bigscreen – 10-foot interface for KDE plasma
Please take my Samsung TV interface
StevenNunez··on Show HN: Jido 2.0, Elixir Agent Framework
A library I'm excited to not vibecode against!
StevenNunez··on Nvidia PersonaPlex 7B on Apple Silicon: Full-Duplex Speech-to-Speech in Swift
I enjoyed unmute.sh too
StevenNunez··on How will OpenAI compete?
It's way too easy to export your context for this to be real. I moved away from ChatGPT from Gemini months ago and haven't thought of it. Paid.
StevenNunez··on You are not supposed to install OpenClaw on your personal computer
What's the fun in that? Also I think /stop would help here.
StevenNunez··on Sub-$200 Lidar could reshuffle auto sensor economics
Time to extend comma.ai!
StevenNunez··on ClawHub
Does Openwork replace the need for openclaw? Seems like a more grown up version of it.
StevenNunez··on Show HN: LocalGPT – A local-first AI assistant in Rust with persistent memory
I've been been using OpenClaw for a bit now and the thing I'm missing is observability. What's this thing thinking/doing right now? Where's my audit log? Every rewrite I see fails to address this.

I feel Elixir and the BEAM would be a perfect language to write this in. Gateways hanging, context window failures exhaustion can be elegantly modeled and remedied with supervision trees. For tracking thoughts, I can dump a process' mailbox and see what it's working on.

StevenNunez··on Qwen3-Coder-Next
This made it work a lot better! Thank you.
StevenNunez··on Qwen3-Coder-Next
Til. Trying it now.
StevenNunez··on Ask HN: Anyone Using a Mac Studio for Local AI/LLM?
I do! I have an M3 Ultra with 512GB. A couple of opencode sessions running work well. Currently running GML 4.7 but was on Kimi K2.5. Both great. Excited for more efficiencies to make their way to LLMs in general.
StevenNunez··on Qwen3-Coder-Next
I tried Coder yesterday with OpenCode... didn't have a great experience. Got caught in a loop reading a single file over and over again until the context filled up. GLM 4.7 has been crushing it so far. One's thinking and other isn't so that's part of it I'm sure.
StevenNunez··on Qwen3-Coder-Next
Not crazy about it. It keeps getting stuck in a loop and filling up the context window (131k, run locally). Kimi's been nice, even if a bit slow.
StevenNunez··on Qwen3-Coder-Next
Going to try this over Kimi k2.5 locally. It was nice but just a bit too slow and a resource hog.
StevenNunez··on OpenClaw – Moltbot Renamed Again
I'll give it a shot. For me it's (promise) is about removing friction. Using the Unix philosophy of small tools, you can send text, voice, image, video to an LLM and (the magic I think) it maintains context over time. So memory is the big part of this.

The next part that makes this compelling is the integration. Mind you, scary stuff, prompt injection, rogue commands, but (BIG BUT) once we figure this out it will provide real value.

Read email, add reminder to register dog with the township, or get an updated referral from your doctor for a therapist. All things that would normally fall through the cracks are organized and presented. I think about all the great projects we see on here, like https://unmute.sh/ and love the idea of having llms get closer to how we interact naturally. I think this gets us closer to that.

StevenNunez··on Comma openpilot – Open source driver-assistance
Ran into this a few days ago while looking for a way out of the subscription hell of self driving offerings. Very excited to watch this space!
StevenNunez··on Nvidia: Natural Conversational AI with Any Role and Voice
Its funny the give away for these is they respond too quickly! Really good though.
StevenNunez··on Pocket TTS: A high quality TTS that gives your CPU a voice
I've moved to https://github.com/readest/readest over audio books in most cases. I just need the dang thing in my ears and their TTS is good enough.
StevenNunez··on Pocket TTS: A high quality TTS that gives your CPU a voice
Great find! unmute was a trip to play with
StevenNunez··on Pixoo Sign Client for Ruby
So cool. Learning about this. Looking forward to playing with it.
StevenNunez··on Microsoft Copilot AI Comes to LG TVs, and Can't Be Deleted
I like FLauncher! Stupid simple and does the job.
StevenNunez··on DoorDash and Waymo launch autonomous delivery service in Phoenix
I'm so thirsty for Elixir success stories I got prematurely excited from the headline
Page 1 of 3Next →