HNHacker News
TopNewBestAskShowJobs

steveharing1

555 karma · joined February 12, 2026

I'm a Software Developer
submissionscomments
steveharing1··on Zig: Build System Reworked
So i checked the license of this project, can anyone pls clarify what is (Expat) after MIT License
steveharing1··on The $500K AI Film That "Premiered at Cannes" Was Not in the Official Festival
Makes sense
steveharing1··on [dead]
Seriously I've seen multiple hypes which were exposed late after false claims spreaded fast and I feel bad for those who don't get to know the truth always
steveharing1··on The $500K AI Film That "Premiered at Cannes" Was Not in the Official Festival
Yes just to hype up their product, they can literally trick people to believe something which is not true at all.
steveharing1··on Nvidia to Spend $150B a Year in Taiwan for AI Infrastructure
You're right but what else he suppose to do? can't ignore taiwan and at the same time can't backoff from his promises as well. Its complicated!
steveharing1··on YouTube to automatically label AI-generated videos
Something, Youtube should have done earlier. But anyway its a good step. But again there are many open models out there on HF that could bypass this just like synthid is not used is every image, similarly not every chinese AI model wants to get their output detected. Time will tell how this goes...
steveharing1··on Microsoft and Uber Are Running into an AI Cost Problem
Yea this makes sense but then why would they even bother to go with claude code earlier?
steveharing1··on Microsoft and Uber Are Running into an AI Cost Problem
I just don't understand why these tech billionaires wanna hype up everything so bad that even they know that people understand its just a unnecessary hype, yet they keep ignoring their core audience and keep on promoting more token usage or should i say wastage of natural resources. I use AI and I believe everyone here does at a certain extent its good but when something is forced, the conclusion comes out bad.
steveharing1··on Search engines alternatives now that Google isn't Google anymore
For me its either bing or duckduckgo
steveharing1··on Google's Next AI Push Is About Agents, Not Chatbots
hmm
steveharing1··on Apple May Add Auto-Deleting Chats to Siri as Gemini Powers Back End AI
Make Sense but again its Siri we are talking about which apple claims to be more private and secure
steveharing1··on Vercel's Zero: A Programming Language Designed for AI Agents
As a developer I understand these error messages existed for decades and I agree with you that its not much of a problem for devs like you and me and many others but that doesnt justify not developing something an ai agent can also work with and its not about devs but more about agents.
steveharing1··on We've made the world too complicated
I agree with this "Our world is an explosion of environmental harm and damage to everything around us." As humans its our responsibility to protect our mother nature by protecting trees and our nature by planting more to at least be able to give back what our nature gave us. I believe if we can't give back then we should not destroy either.
steveharing1··on OpenAI is connecting ChatGPT to bank accounts via Plaid
It won't go wrong if you don't wanna use this feature but if you do then its upto you that you''re trusting a for profit company that much that you provide them with your confidential data.
steveharing1··on OpenAI is connecting ChatGPT to bank accounts via Plaid
You absolutely do not have to use the new financial feature. Its optional
steveharing1··on Explore Wikipedia Like a Windows XP Desktop
What a beautiful nostalgic feeling. Keep up the good work! Worth adding some start menu options as well.
steveharing1··on Claude Platform on AWS
At least now we can expect more usage limits.
steveharing1··on ZAYA1-8B: An 8B Moe Model with 760M Active Params Matching DeepSeek-R1 on Math
He could be right but time will tell if we can really achieve that level in open source space because as you know Even in open source space companies go closed when they achieve something really efficient and frontier. I'm not talking about all but that's usually a pattern
steveharing1··on ZAYA1-8B matches DeepSeek-R1 on math with less than 1B active parameters
You couldn't be any more right!
steveharing1··on ZAYA1-8B matches DeepSeek-R1 on math with less than 1B active parameters
That's absolutely possible, its just as we move towards more advancement, We'll soon see Small models being smart enough to not be judged by parameter count but their reasoning and intelligence. You can see examples like Qwen 3.6 27B.
steveharing1··on Train Your Own LLM from Scratch
The documentation is really helpful enough to get started
steveharing1··on Remodex: Control Codex from Your iPhone
Neat local first setup to control Codex on your Mac from an iPhone. Uses a paired encrypted session and keeps everything self hosted.
steveharing1··on AI Coding Models You Can Run Locally on Consumer Hardware
Can u suggest as per your experience what model you use and is it giving you intermediate to best coding results in your setup?
steveharing1··on Open Design: Use Your Coding Agent as a Design Engine
nice work!
steveharing1··on Open Design: Use Your Coding Agent as a Design Engine
I really appreciate open source community for moving this fast
steveharing1··on Granite 4.1: IBM's 8B Model Matching 32B MoE
yes. I've used it a lot. its very simple and good
steveharing1··on Granite 4.1: IBM's 8B Model Matching 32B MoE
You can try Open WebUI. Its genuinely useful when it comes to running open models locally with a clean interface
steveharing1··on Granite 4.1: IBM's 8B Model Matching 32B MoE
even calling it roll of the dice is an assumption. Can you point anything you find as mistake?
steveharing1··on Granite 4.1: IBM's 8B Model Matching 32B MoE
Thanks for letting me know
steveharing1··on Granite 4.1: IBM's 8B Model Matching 32B MoE
Because Qwen 3.6 pushes way above its weight. Granite 8B is impressive, but Qwen still wins on raw capability, especially for coding.
Page 1 of 3Next →