HackerLangs
トップ新着トレンドコメント過去質問紹介求人

pdyc

no profile record

投稿

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

simonwillison.net
624 ポイント·投稿者 pdyc·先月·769 コメント

Show HN: HTML/React/Tailwind snippet preview, annotation and secure sharing tool

easyanalytica.com
1 ポイント·投稿者 pdyc·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 pdyc·3 か月前·0 コメント

Zuckerberg Launches Meta Small Business

axios.com
2 ポイント·投稿者 pdyc·4 か月前·0 コメント

When the line stops going up

coryzue.com
2 ポイント·投稿者 pdyc·6 か月前·0 コメント

Adobe to Buy Semrush for $1.9B

cnbc.com
6 ポイント·投稿者 pdyc·8 か月前·0 コメント

Amazon cloud records 20% sales growth, topping estimates

cnbc.com
4 ポイント·投稿者 pdyc·8 か月前·0 コメント

My Evil Plan If I Were Mark Zuckerberg

newbeelearn.com
1 ポイント·投稿者 pdyc·8 か月前·0 コメント

What's Next for iPad Pro? A Vapor Chamber Like iPhone 17 Pro, Ads in Maps

bloomberg.com
7 ポイント·投稿者 pdyc·9 か月前·1 コメント

China's Xiaomi says surging memory chip prices push up smartphone costs

reuters.com
1 ポイント·投稿者 pdyc·9 か月前·0 コメント

Does productivity increases with AI or it just feels like it?

newbeelearn.com
3 ポイント·投稿者 pdyc·9 か月前·0 コメント

WhatsApp changes its terms to bar general purpose chatbots from its platform

techcrunch.com
6 ポイント·投稿者 pdyc·9 か月前·0 コメント

How An Obscure Feature of a Long Forgotten SideProject Saved the Day

newbeelearn.com
2 ポイント·投稿者 pdyc·9 か月前·0 コメント

[untitled]

1 ポイント·投稿者 pdyc·9 か月前·0 コメント

コメント

pdyc
·23 日前·議論
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.
pdyc
·25 日前·議論
what bug and it affects what?
pdyc
·25 日前·議論
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
pdyc
·26 日前·議論
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.
pdyc
·先月·議論
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
pdyc
·先月·議論
afaik, enterprise plans are not subsidized. its 20$/seat+api pricing. Unless you are saying api pricing itself is subsidized.
pdyc
·2 か月前·議論
depends on how clear your instructions are, if there is no ambiguity you can even use gemma4 e2b/e4b.
pdyc
·2 か月前·議論
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.
pdyc
·2 か月前·議論
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.
pdyc
·2 か月前·議論
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.
pdyc
·2 か月前·議論
- 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
pdyc
·2 か月前·議論
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.
pdyc
·3 か月前·議論
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/
pdyc
·3 か月前·議論
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 :-)
pdyc
·3 か月前·議論
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.
pdyc
·3 か月前·議論
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
pdyc
·3 か月前·議論
i dont get it, mac has unified memory how would offloading experts to cpu help?
pdyc
·3 か月前·議論
can you elaborate? you can use quantized version, would context still be an issue with it?
pdyc
·3 か月前·議論
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.
pdyc
·3 か月前·議論
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.