Hacker News: armanj

New comment by armanj in "Python 3.15: features that didn't make the headlines"

armanj — Thu, 21 May 2026 13:59:30 +0000

funny how we may have to wait even longer for llms to pick up this update in their pre-training

New comment by armanj in "An OpenAI model has disproved a central conjecture in discrete geometry"

armanj — Thu, 21 May 2026 01:23:08 +0000

useless fact: there is no mention to "gpt" in this article. the ai is referred to as "An internal OpenAI model".

New comment by armanj in "Computer Hobby Movement in Canada"

armanj — Thu, 14 May 2026 14:23:26 +0000

I'm in Toronto and I can confirm.

New comment by armanj in "MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble"

armanj — Wed, 13 May 2026 23:16:34 +0000

i assumed you're connected to internet and using codex/claude code

New comment by armanj in "MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble"

armanj — Wed, 13 May 2026 20:13:17 +0000

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.

New comment by armanj in "AlphaEvolve: Gemini-powered coding agent scaling impact across fields"

armanj — Thu, 07 May 2026 19:21:53 +0000

seems like `karpathy/autoresearch` on steroids

New comment by armanj in "Agents can now create Cloudflare accounts, buy domains, and deploy"

armanj — Wed, 06 May 2026 04:04:20 +0000

> buy

good luck

New comment by armanj in "Incident with Actions – Resolved"

armanj — Tue, 05 May 2026 16:17:43 +0000

How reliable is this uptime? and why it's sooo different from gh's official status numbers?

New comment by armanj in "Zed 1.0"

armanj — Wed, 29 Apr 2026 22:08:06 +0000

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.

New comment by armanj in "DeepSeek v4"

armanj — Fri, 24 Apr 2026 15:06:23 +0000

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"

New comment by armanj in "SpaceX says it has agreement to acquire Cursor for $60B"

armanj — Wed, 22 Apr 2026 00:18:29 +0000

hn is this true

New comment by armanj in "Ternary Bonsai: Top Intelligence at 1.58 Bits"

armanj — Tue, 21 Apr 2026 01:32:51 +0000

I did a quick benchmark & compared it with Qwen3.5: https://github.com/ArmanJR/PrismML-Bonsai-vs-Qwen3.5-Benchma...

in my results, accuracy-wise Ternary-Bonsai-8B is on par with Qwen3.5-4B. But in accuracy-per-byte, bonsai is the clear winner:

=> Ternary-Bonsai-1.7B achieved 65.1% from 462 MiB, beating Qwen3.5-0.8B by 12 points while being ~5% smaller on disk. => Ternary-Bonsai-4B is the accuracy-per-byte winner above 1 GiB. 83.0% from only 1.1 GiB, within 2 points of Qwen3.5-4B at 40% of the weight size.

they show strong promise on edge devices and where disk space is limited. I think this lab is worth watching.

New comment by armanj in "Claude Opus 4.7"

armanj — Thu, 16 Apr 2026 17:16:46 +0000

while it seems even with 4.7 we will never see the quality of early 4.6 days, some dude is posting 'agi arrived!!!' on instagram and linkedIn.

New comment by armanj in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

armanj — Thu, 16 Apr 2026 14:12:35 +0000

I recall a Qwen exec posted a public poll on Twitter, asking which model from Qwen3.6 you want to see open-sourced; and the 27b variant was by far the most popular choice. Not sure why they ignored it lol.

New comment by armanj in "Reverse engineering Gemini's SynthID detection"

armanj — Thu, 09 Apr 2026 21:12:02 +0000

kinda ironic you can clearly see signs of Claude, as it shows misaligning table walls in the readme doc

New comment by armanj in "Google open-sources experimental agent orchestration testbed Scion"

armanj — Tue, 07 Apr 2026 17:57:21 +0000

> This project is early and experimental. Core concepts are settled, but expect rough edges. Local mode: relatively stable - Hub-based workflows: ~80% verified - Kubernetes runtime: early with known rough edges

i guess gastown is a better choice for now? idk i don't feel good about "relatively stable"

New comment by armanj in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

armanj — Sat, 04 Apr 2026 03:24:43 +0000

People in the comments are, in my opinion, overcomplicating this and making it more philosophical than it needs to be. The reason for their decision is dead simple: there aren’t enough GPUs, so they have to cut access somewhere, and they’re starting with claw.

It’s really that straightforward. If tomorrow they decide GPUs are better allocated to enterprise use, they could start removing the $20 plan just as quickly overnight, the same way they did tonight.

New comment by armanj in "The Claude Code Source Leak: fake tools, frustration regexes, undercover mode"

armanj — Tue, 31 Mar 2026 19:40:38 +0000

> Anti-distillation: injecting fake tools to poison copycats

Does this mean `huggingface.co/Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled` is unusable? Had anyone seen fake tool calls working with this model?

New comment by armanj in "Claude Code's source code has been leaked via a map file in their NPM registry"

armanj — Tue, 31 Mar 2026 13:58:31 +0000

claude code started as an experimental project by boris cherny. when you’re experimenting, you naturally use the language you’re most comfortable with. as the project grew, more people got involved and it evolved from there. codex, on the other hand, was built from the start specifically to compete with claude code. they chose rust early on because they knew it was going to be big.

New comment by armanj in "Voyager 1 runs on 69 KB of memory and an 8-track tape recorder"

armanj — Sun, 29 Mar 2026 18:31:44 +0000

A well defined doc evolves over time. it gets sharper with real-world scenarios, incidents, and experiments. Before Voyager 1, we didn’t have that kind of experience. You can’t predict everything upfront.

> Theory only takes you so far