Hacker News: armanjhttps://news.ycombinator.com/user?id=armanjHacker News RSShttps://hnrss.org/hnrss v2.1.1Tue, 18 Aug 2026 14:54:08 +0000<![CDATA[New comment by armanj in "AI;DR (AI; Didn't Read)"]]>You're absolutely right

]]>Mon, 17 Aug 2026 20:24:57 +0000https://news.ycombinator.com/item?id=49337104armanjhttps://news.ycombinator.com/item?id=49337104https://news.ycombinator.com/item?id=49337104<![CDATA[Using math for solving real-life problems]]>Article URL: https://app.notion.com/p/Number-Pi-Podcast-E09-3b46c4fc04cb8077aad7fb4d4b1eb6cc

Comments URL: https://news.ycombinator.com/item?id=49275183

Points: 2

# Comments: 0

]]>Wed, 12 Aug 2026 16:42:07 +0000https://app.notion.com/p/Number-Pi-Podcast-E09-3b46c4fc04cb8077aad7fb4d4b1eb6ccarmanjhttps://news.ycombinator.com/item?id=49275183https://news.ycombinator.com/item?id=49275183<![CDATA[New comment by armanj in "Advancing the price-performance frontier with GPT‑5.6"]]>https://developers.openai.com/api/docs/models/gpt-realtime-2...

]]>Fri, 31 Jul 2026 14:22:13 +0000https://news.ycombinator.com/item?id=49123527armanjhttps://news.ycombinator.com/item?id=49123527https://news.ycombinator.com/item?id=49123527<![CDATA[New comment by armanj in "Advancing the price-performance frontier with GPT‑5.6"]]>any particular reason not using terra or sol, given the generous limit quotas and frequent codex resets?

]]>Fri, 31 Jul 2026 05:05:18 +0000https://news.ycombinator.com/item?id=49119214armanjhttps://news.ycombinator.com/item?id=49119214https://news.ycombinator.com/item?id=49119214<![CDATA[New comment by armanj in "Advancing the price-performance frontier with GPT‑5.6"]]>might as well rethink about their pricing on gpt-realtime. for a quick test, spoke to that model for ~5 minutes, ended up spending near $1.

]]>Fri, 31 Jul 2026 05:04:00 +0000https://news.ycombinator.com/item?id=49119205armanjhttps://news.ycombinator.com/item?id=49119205https://news.ycombinator.com/item?id=49119205<![CDATA[New comment by armanj in "$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol"]]>the moment debate becomes philosophical it's over

]]>Fri, 17 Jul 2026 13:56:34 +0000https://news.ycombinator.com/item?id=48947460armanjhttps://news.ycombinator.com/item?id=48947460https://news.ycombinator.com/item?id=48947460<![CDATA[New comment by armanj in "Bonsai 27B: A 27B-Class model that runs on a phone"]]>Bonsai 8B and 1.7B were on Qwen3.5 the benchmark is from a few months ago. However I'll add Qwen3.6 to the benchmark too.

]]>Tue, 14 Jul 2026 22:36:33 +0000https://news.ycombinator.com/item?id=48913810armanjhttps://news.ycombinator.com/item?id=48913810https://news.ycombinator.com/item?id=48913810<![CDATA[New comment by armanj in "Bonsai 27B: A 27B-Class model that runs on a phone"]]>Bonsai vs Qwen (quick) Benchmark: https://github.com/ArmanJR/PrismML-Bonsai-vs-Qwen3.5-Benchma...

]]>Tue, 14 Jul 2026 22:20:40 +0000https://news.ycombinator.com/item?id=48913668armanjhttps://news.ycombinator.com/item?id=48913668https://news.ycombinator.com/item?id=48913668<![CDATA[New comment by armanj in "Show HN: Davit, a Apple Containers UI"]]>can someone tldr me why choose apple container (and its ui) over docker (and orbstack)

]]>Tue, 07 Jul 2026 23:47:14 +0000https://news.ycombinator.com/item?id=48825567armanjhttps://news.ycombinator.com/item?id=48825567https://news.ycombinator.com/item?id=48825567<![CDATA[New comment by armanj in "How to sequence your own DNA at home"]]>one main marketing leverage of 23andMe, AncestryDNA, etc are fulfilling the curiosity of people who want to know which part of the world their genes are from. I guess that dataset should be preparatory.

]]>Tue, 07 Jul 2026 03:08:42 +0000https://news.ycombinator.com/item?id=48813274armanjhttps://news.ycombinator.com/item?id=48813274https://news.ycombinator.com/item?id=48813274<![CDATA[New comment by armanj in "Python 3.15: features that didn't make the headlines"]]>funny how we may have to wait even longer for llms to pick up this update in their pre-training

]]>Thu, 21 May 2026 13:59:30 +0000https://news.ycombinator.com/item?id=48222689armanjhttps://news.ycombinator.com/item?id=48222689https://news.ycombinator.com/item?id=48222689<![CDATA[New comment by armanj in "An OpenAI model has disproved a central conjecture in discrete geometry"]]>useless fact: there is no mention to "gpt" in this article. the ai is referred to as "An internal OpenAI model".

]]>Thu, 21 May 2026 01:23:08 +0000https://news.ycombinator.com/item?id=48216632armanjhttps://news.ycombinator.com/item?id=48216632https://news.ycombinator.com/item?id=48216632<![CDATA[New comment by armanj in "Computer Hobby Movement in Canada"]]>I'm in Toronto and I can confirm.

]]>Thu, 14 May 2026 14:23:26 +0000https://news.ycombinator.com/item?id=48135865armanjhttps://news.ycombinator.com/item?id=48135865https://news.ycombinator.com/item?id=48135865<![CDATA[New comment by armanj in "MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble"]]>i assumed you're connected to internet and using codex/claude code

]]>Wed, 13 May 2026 23:16:34 +0000https://news.ycombinator.com/item?id=48128927armanjhttps://news.ycombinator.com/item?id=48128927https://news.ycombinator.com/item?id=48128927<![CDATA[New comment by armanj in "MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble"]]>for vibe coding stuff, especially when you're outside touching grass, I believe MacBook Neo is perfect. it fills the gap between the phone remote control (which is too painful for chatting with ai cli) and, well, not having any dev device.

]]>Wed, 13 May 2026 20:13:17 +0000https://news.ycombinator.com/item?id=48126864armanjhttps://news.ycombinator.com/item?id=48126864https://news.ycombinator.com/item?id=48126864<![CDATA[New comment by armanj in "AlphaEvolve: Gemini-powered coding agent scaling impact across fields"]]>seems like `karpathy/autoresearch` on steroids

]]>Thu, 07 May 2026 19:21:53 +0000https://news.ycombinator.com/item?id=48053628armanjhttps://news.ycombinator.com/item?id=48053628https://news.ycombinator.com/item?id=48053628<![CDATA[New comment by armanj in "Agents can now create Cloudflare accounts, buy domains, and deploy"]]>> buy

good luck

]]>Wed, 06 May 2026 04:04:20 +0000https://news.ycombinator.com/item?id=48032029armanjhttps://news.ycombinator.com/item?id=48032029https://news.ycombinator.com/item?id=48032029<![CDATA[New comment by armanj in "Incident with Actions – Resolved"]]>How reliable is this uptime? and why it's sooo different from gh's official status numbers?

]]>Tue, 05 May 2026 16:17:43 +0000https://news.ycombinator.com/item?id=48024604armanjhttps://news.ycombinator.com/item?id=48024604https://news.ycombinator.com/item?id=48024604<![CDATA[New comment by armanj in "Zed 1.0"]]>i've been a zed user for almost 6 months. i've encountered maaany bugs which i reported, or that were already reported. they're still there. meanwhile, every single update shipped a feature or bugfix for "ai agents".

not sure how 1.0 ships with that massive pile of bugs. but ai agents are the first-class citizen in this editor, and developer experience is not a priority.

funny thing is i uninstalled zed right before the 1.0 release. kinda relieved i didn't miss anything.

]]>Wed, 29 Apr 2026 22:08:06 +0000https://news.ycombinator.com/item?id=47955383armanjhttps://news.ycombinator.com/item?id=47955383https://news.ycombinator.com/item?id=47955383<![CDATA[New comment by armanj in "DeepSeek v4"]]>I have a few lightweight apps using deepseek api, and funny how the initial credit I topped up for using r1 is still left. Nothing makes the user happier than getting more for less. cc: anthropics with its fancy token-wasting claude code "features"

]]>Fri, 24 Apr 2026 15:06:23 +0000https://news.ycombinator.com/item?id=47891280armanjhttps://news.ycombinator.com/item?id=47891280https://news.ycombinator.com/item?id=47891280