Hacker News: pdyc

New comment by pdyc in "OpenClaw 2.0, Accidentally"

pdyc — Mon, 31 Aug 2026 12:40:15 +0000

what are you using for reading/writing pdf? is it some mcp plugin or some pdf lib in python/js and qwen is doing it via code?

New comment by pdyc in "Tool that finds hidden opportunities in your Google Search Console data"

pdyc — Wed, 26 Aug 2026 14:37:30 +0000

GSC Insight is a free browser-based tool that turns Google Search Console CSV exports into a visual SEO dashboard.

It helps you quickly spot:

- Quick-win keywords

- Content gaps

- Page and query opportunities

- Branded vs. non-branded traffic

- Ranking and click distribution

- Country-level performance

You can also add your logo and add title and create reports

- Free

- No Registration/login

- No installations(online)

- No GSC connection or server upload

- works offline after first load - your CSV data is processed locally in the browser.

Tool that finds hidden opportunities in your Google Search Console data

pdyc — Wed, 26 Aug 2026 14:37:30 +0000

Article URL: https://easyanalytica.com/tools/gsc-insight/

Comments URL: https://news.ycombinator.com/item?id=49449999

Points: 2

# Comments: 1

New comment by pdyc in "Qwen 3.8 27B is excellent, but it defaults to overthinking things"

pdyc — Tue, 18 Aug 2026 04:09:16 +0000

i am using llama.cpp with pi harness on linux(cachyos). some of the things like coopmat are disabled in linux due to intel driver issues otherwise performance would be even better.

New comment by pdyc in "Qwen 3.8 27B is excellent, but it defaults to overthinking things"

pdyc — Mon, 17 Aug 2026 05:57:22 +0000

i have same 255h and i was able to run it with low token speed 6-8tg/s with approx similar context window 60k

Anthropic investors bet on $2T valuation in record IPO

pdyc — Thu, 13 Aug 2026 16:11:36 +0000

Article URL: https://www.ft.com/content/840ac156-af1c-4a82-b260-ae791072fcfa

Comments URL: https://news.ycombinator.com/item?id=49288124

Points: 7

# Comments: 1

New comment by pdyc in "You only need the frontier model for one single edit"

pdyc — Tue, 21 Jul 2026 06:01:57 +0000

+1. i have similar workflow and i use local models on igpu so token cost is free and electricity cost is in cents.

New comment by pdyc in "X permanently banned my 15-year-old account for sharing my own open-source lib"

pdyc — Fri, 17 Jul 2026 07:10:52 +0000

yes, happened to me as well on sideprojects and it continues, i am able to post on other groups, its weird.

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

pdyc — Mon, 13 Jul 2026 05:06:14 +0000

I am building https://EasyAnalytica.com - single place for all your dashboards. It generates dashboards automatically from data without using ai. It supports getting data from google sheets, api's, url's etc. I have recently added support for gsc as data source and i plan to continue adding more in coming weeks.

New comment by pdyc in "Emacs 31 Is Around the Corner: The Changes I'm Daily Driving"

pdyc — Thu, 18 Jun 2026 14:20:35 +0000

I have been using Emacs for more than a decade, and I was always excited about the features. But with AI, something has changed. I no longer type/edit that much. Recently, LSP stopped working, and I was completely oblivious to it for about a week. Earlier, something like this would have been a major annoyance.

New comment by pdyc in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

pdyc — Tue, 16 Jun 2026 05:06:46 +0000

what bug and it affects what?

New comment by pdyc in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

pdyc — Tue, 16 Jun 2026 04:32:47 +0000

yes

harness - pi+custom extension for subagents

model - qwen3.6 35ba3b q4km

hardware - intel arrow lake with 32gb ram

server - llama.cpp vulkan

performance - 15-18t/s generation 50-150t/s pp

planning and task creation is still using claude/gpt but they dont touch the code. All coding is done using this setup.

Example of project made using this setup easyanalytica.com , its of medium size complexity

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

pdyc — Mon, 15 Jun 2026 05:49:42 +0000

i am still working on easyanalytica tool to auto generate dashboards without ai . I recently added comparison feature and figuring that out was fun. There are lot of interesting ideas on execution side of it but for end user its a simple product, just give data and see the dashboard.

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: 769

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.