Hacker News: dr_kiszonka

New comment by dr_kiszonka in "Mouseless – keyboard-driven control of macOS/Linux/Windows"

dr_kiszonka — Fri, 05 Jun 2026 17:10:27 +0000

Does Mouseless support multiple monitors?

I have been trying out similar software for a few years but haven't seen one that would let me "click" outside the main monitor on Windows.

New comment by dr_kiszonka in "MAI-Thinking-1"

dr_kiszonka — Wed, 03 Jun 2026 08:41:43 +0000

When would a larger model have a smaller inference footprint? If the larger was MoE and the smaller was dense?

New comment by dr_kiszonka in "Please don't spam people looking for employment. It's just cruel"

dr_kiszonka — Tue, 02 Jun 2026 15:40:29 +0000

This is great! I haven't heard of gmailctl before.

New comment by dr_kiszonka in "Show HN: Komi-learn – continuous memory and self-improvement for coding agents"

dr_kiszonka — Sun, 31 May 2026 20:54:54 +0000

> than a structured collection of md files.

I think it depends on what a memory system includes. Those that automatically inject relevant information into context are in my experience better than just md docs because agents often ignore, forget to read, or don't read md files in full.

New comment by dr_kiszonka in "AI job grief: A psychological crisis hitting tech workers"

dr_kiszonka — Sun, 31 May 2026 20:45:48 +0000

It isn't ideal, but I am starting to write code (with AI tab completions) while waiting for LLMs. The tab completions are sometimes overeager and I wish I had more control over them, but at least I am not staring at "Thinking" all day. Having said that sometimes you have to monitor AI because, e.g., AGY CLI, often goes off the rails completely, including writing code outside of the "sandbox."

New comment by dr_kiszonka in "Real-time LLM Inference on Standard GPUs: 3k tokens/s per request"

dr_kiszonka — Fri, 29 May 2026 17:15:44 +0000

Thank you for explaining. Do you think there are still opportunities for stack optimizations to meaningfully speed up inference on single consumer-grade GPUs?

New comment by dr_kiszonka in "Codex-maxxing"

dr_kiszonka — Tue, 19 May 2026 22:23:02 +0000

I am lost. Codex can't look up stuff for you in your codebase? GitHub Copilot can't look up PRs for you?

New comment by dr_kiszonka in "Codex-maxxing"

dr_kiszonka — Tue, 19 May 2026 15:26:29 +0000

For Codex, that is ChatGPT? https://openai.com/index/work-with-codex-from-anywhere/

Or do you want it to speak to you too? I think this would have to be TTS on your phone. You can have ChatGPT speak to you but I don't see that feature in Codex.

Cardputer Zero – Pocket Raspberry Pi Computer for Hackers

dr_kiszonka — Tue, 19 May 2026 15:05:10 +0000

Article URL: https://shop.m5stack.com/pages/m5-cardputerzero

Comments URL: https://news.ycombinator.com/item?id=48194317

Points: 3

# Comments: 0

New comment by dr_kiszonka in "Show HN: Files.md – Open-source alternative to Obsidian"

dr_kiszonka — Mon, 18 May 2026 16:44:48 +0000

Very nice! Would you have any recommendations for the leanest compatible "host"? Instead of adding this to my VSCode, I would rather use it as a separate app. Currently, I use a naked Zed install for Markdown because it launches faster than my system apps (and than Cursor, VSCode, etc.).

New comment by dr_kiszonka in "Show HN: Browser based sythesizer, drum machine and squencer"

dr_kiszonka — Sun, 17 May 2026 04:06:12 +0000

I like the idea. The demo music is very cool. The problem with using tone.js for such projects is, as I have learned the hard way, that it is hard to avoid issues like clipping; and AI agents are surprisingly bad at optimizing such apps.

I test nearly every new model that I can access on building a modular groovebox and they keep making the same mistakes. Even a 4-channel 16-step with a playhead can give them trouble.

New comment by dr_kiszonka in "OpenClaw Creator Spent $1.3M on OpenAI Tokens in 30 Days"

dr_kiszonka — Sun, 17 May 2026 03:08:06 +0000

> I spend more time refinding prd , epics and stories than I do elbows deep in code.

And do you enjoy this more than writing code? I used to look forward to writing code, solving these little optimization puzzles, learning, and staying sharp. Working with agents is dreadful in comparison. They lie, rarely learn, and I feel like a proctor.

Sure, you sometimes get to see something amazing, but usually I am just very annoyed by their performance and ever-changing but never-ending billing issues. First, with Claude Code, now with Codex, which was fine for a minute, but now I am out of tokens for the majority of time. (I don't have the income for those Pro INTx plans.)

New comment by dr_kiszonka in "Google broke reCAPTCHA for de-googled Android users"

dr_kiszonka — Sat, 09 May 2026 06:05:45 +0000

Reckless Condensed?

Casio S100X Japanese Lacquer Edition (JP Page Only)

dr_kiszonka — Thu, 07 May 2026 12:09:47 +0000

Article URL: https://www.casio.com/jp/basic-calculators/premium/en-s100x-jc1-u/

Comments URL: https://news.ycombinator.com/item?id=48048407

Points: 322

# Comments: 156

New comment by dr_kiszonka in "Appearing productive in the workplace"

dr_kiszonka — Wed, 06 May 2026 21:19:13 +0000

I work under the assumption that the primary audience of everything I write at work is an AI. Managers will take what I send and have it summarized and evaluated by some chatbot or agent. (Of course, I cannot send them the summary myself.)

So like ATS checkers for resumes, I find myself needing an AI checker for my text.

Ultimately, we will have AI write everything for another AI to parse, which will be a massive waste of energy. If only there was some agreed-upon set of rules, structures, standards, and procedures to facilitate a more efficient communication...

New comment by dr_kiszonka in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

dr_kiszonka — Wed, 06 May 2026 06:08:14 +0000

You can fine-tune relatively easily in Unsloth Studio.

New comment by dr_kiszonka in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

dr_kiszonka — Wed, 06 May 2026 05:49:16 +0000

Was this a script using the API or something you asked Gemini CLI to do? I burn through Gemini CLI and Antigravity daily quotas in 2 hours on the $20 plan (AI Pro). Or maybe you used an older flash model?

I am asking because I am very frustrated with the new quotas and I am hoping to get more mileage out of my subscription.

New comment by dr_kiszonka in "Claude Code refuses requests or charges extra if your commits mention "OpenClaw""

dr_kiszonka — Fri, 01 May 2026 05:45:43 +0000

Would you mind sharing what specific Qwen model you are running and how (Llama, vLLM, etc.)?

New comment by dr_kiszonka in "Claude Code refuses requests or charges extra if your commits mention "OpenClaw""

dr_kiszonka — Fri, 01 May 2026 05:35:45 +0000

Don't worry. AGI will be vibe-coded too.

New comment by dr_kiszonka in "Men who stare at walls"

dr_kiszonka — Tue, 28 Apr 2026 05:47:53 +0000

I am a pretty peaceful person, but working with agents frequently (daily) makes me furious. I wonder if the context switching you mentioned leads to more fatigue, which makes me much more irritable.