Hacker News: pdyc

New comment by pdyc in "Ask HN: What are tools you have made for yourself since the advent of AI?"

pdyc — Tue, 09 Jun 2026 05:41:15 +0000

html snippet playground - for testing html/react snippets

token speed calculator - for estimating tg/s of ai based on ram speed and model size/params this helps in comparing different hw, estimating likely speeds i will get on hardware

prompt assembler - to create prompt and context once and reuse it in different ai's, picking and choosing context in a prompt, creating agent.md etc.

dashboard builder - for viewing gsc, ga, stripe data in one place

New comment by pdyc in "Uber's $1,500/month AI limit is a useful signal for AI tool pricing"

pdyc — Wed, 03 Jun 2026 13:18:56 +0000

afaik, enterprise plans are not subsidized. its 20$/seat+api pricing. Unless you are saying api pricing itself is subsidized.

Uber's $1,500/month AI limit is a useful signal for AI tool pricing

pdyc — Wed, 03 Jun 2026 12:25:14 +0000

https://www.bloomberg.com/news/articles/2026-06-02/uber-caps... (https://archive.ph/ZrwAy)

Comments URL: https://news.ycombinator.com/item?id=48383056

Points: 624

# Comments: 770

New comment by pdyc in "Using AI to write better code more slowly"

pdyc — Tue, 26 May 2026 05:07:07 +0000

depends on how clear your instructions are, if there is no ambiguity you can even use gemma4 e2b/e4b.

New comment by pdyc in "Running local models on an M4 with 24GB memory"

pdyc — Tue, 12 May 2026 04:33:14 +0000

i did not see much improvement for my use case i.e. file editing tasks but with e4b tg/s is lower so i stick with e2b.

New comment by pdyc in "Running local models on an M4 with 24GB memory"

pdyc — Mon, 11 May 2026 12:33:12 +0000

yes i keep on trying small models, i have also tried qwen 3.5 0.8B, 2B, 4b and gemma4 e4B models but they either did not worked reliably (thinking loop, issue in following instruction) or there were performance issues (prompt speed, tg speed, too much ram) e2b was the sweet spot where i could give it plan and it can edit files properly.

New comment by pdyc in "Running local models on an M4 with 24GB memory"

pdyc — Mon, 11 May 2026 06:28:08 +0000

i use smaller model gemma e2b for most of my editing and it works surprisingly well. Workflow is planning with sota models and execution via small models. If you plan properly dont leave ambiguity for smaller model it works well.

New comment by pdyc in "Ask HN: What are you working on? (May 2026)"

pdyc — Mon, 11 May 2026 05:05:15 +0000

- Tool for organizing files, pasted data, and prompts into markdown snippets you can copy into different AI chats.

- Calculator that gives tg/s and vram required based on model params and ddr settings.

- Auto create dashboard from csv/json files or apis Easyanalytica.com

- snippet viewer for html/react that allows annotation and sharing based on url fragments

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

pdyc — Thu, 30 Apr 2026 16:01:41 +0000

why do people want to continue to use anthropic despite their shitty service? its not like they have some kind of lock-in as it is still new company and it has shown its color before we are stuck with it unlike google/meta etc.

New comment by pdyc in "nowhere: an entire website encoded in a URL"

pdyc — Fri, 24 Apr 2026 13:34:47 +0000

I did a showhn with similar idea(got a whooping 1 point and was flagged as spam which was later removed by mods), you paste your html and it encodes it into url, you can share the url without server involvement. I even added a url shortener because while technically feasible encoded url becomes long and QR code no longer works reliably. I also added annotation so you can add your comments and pass it to colleagues.

https://easyanalytica.com/tools/html-playground/

New comment by pdyc in "Show HN: VidStudio, a browser based video editor that doesn't upload your files"

pdyc — Tue, 21 Apr 2026 18:01:19 +0000

that guy is not including ffmpeg and is not encoding in browser. What he is doing is generating a ffmpeg command that you can run on your cli/scripts etc.

PS: i am that guy :-)

New comment by pdyc in "GitHub's Fake Star Economy"

pdyc — Mon, 20 Apr 2026 13:43:19 +0000

i was with them until

"We ran our own analysis sampling 150 profiles per repo across 20 projects and found repos where 36-76% of stargazers have zero followers and fork-to-star ratios 10x below organic baselines"

This does not looks like appropriate signal to use on github, i doubt that this is organic baseline.If this is used as metric than study might be flawed.

New comment by pdyc in "Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All"

pdyc — Thu, 16 Apr 2026 14:20:38 +0000

correct but it should be some ratio of model size like if model size is x GB, max context would occupy x * some constant of RAM. For quantized version assuming its 18GB for Q4 it should be able to support 64-128k with this mac

New comment by pdyc in "Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All"

pdyc — Thu, 16 Apr 2026 14:18:43 +0000

i dont get it, mac has unified memory how would offloading experts to cpu help?

New comment by pdyc in "Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All"

pdyc — Thu, 16 Apr 2026 14:12:51 +0000

can you elaborate? you can use quantized version, would context still be an issue with it?

New comment by pdyc in "Do you even need a database?"

pdyc — Thu, 16 Apr 2026 12:53:46 +0000

what was your data size? i am surprised 800kb made a difference? using stringzilla was smart approach,my guess is it being unusually faster made all the difference.

New comment by pdyc in "Show HN: SmallDocs - Markdown without the frustrations"

pdyc — Thu, 16 Apr 2026 12:42:25 +0000

i doubt it would be possible, it boils down to compression problem compressing x amount of content to y bits, since content is unpredictable it cannot be done without having intermediary to store it.

New comment by pdyc in "Show HN: SmallDocs - Markdown without the frustrations"

pdyc — Thu, 16 Apr 2026 11:35:31 +0000

i also used fragment technique for sharing html snippets but url's became very long, i had to implement optional url shortener after users complained. Unfortunately that meant server interaction.

https://easyanalytica.com/tools/html-playground/

New comment by pdyc in "Ask HN: What Are You Working On? (April 2026)"

pdyc — Mon, 13 Apr 2026 04:57:36 +0000

Too many things

- Tool to auto create dashboards from csv/json files or rest api ( https://EasyAnalytica.com )

- Tool to preview, annotate and share html snippets ( https://easyanalytica.com/tools/html-playground/ )

- Creating agent to edit files with smaller model(<1B) not yet released.

-Prompt assember to create prompts/templates/context and easily share between ai to be released this week.

New comment by pdyc in "Moving from WordPress to Jekyll (and static site generators in general)"

pdyc — Fri, 10 Apr 2026 06:38:07 +0000

wow that looks beautiful. I want to migrate my hugo site to astro because astro is easier to manage and more friendly to local llm's than hugo but postponing it.