HackerTrans
トップ新着トレンドコメント過去質問紹介求人

akshay326

no profile record

投稿

Show HN: Using RasPi and Qwen 2.5 VL to find out when birds visit my balcony

akshay326.com
4 ポイント·投稿者 akshay326·3 か月前·0 コメント

[untitled]

1 ポイント·投稿者 akshay326·4 か月前·0 コメント

[untitled]

1 ポイント·投稿者 akshay326·5 か月前·0 コメント

More than one-third of cancer cases are preventable, a study finds

scientificamerican.com
3 ポイント·投稿者 akshay326·5 か月前·0 コメント

[untitled]

1 ポイント·投稿者 akshay326·5 か月前·0 コメント

Ask HN: How to prevent Claude/GPT/Gemini from reinforcing your biases?

30 ポイント·投稿者 akshay326·6 か月前·22 コメント

Show HN: Open-source welcome email automation: Supabase + Gmail + Seer

youtube.com
1 ポイント·投稿者 akshay326·6 か月前·1 コメント

Show HN: 3D Visualizing YC Advice

github.com
2 ポイント·投稿者 akshay326·6 か月前·0 コメント

Pre-commit lint checks: Vibe coding's kryptonite

getseer.dev
16 ポイント·投稿者 akshay326·6 か月前·27 コメント

Space Forge plans to manufacture semiconductors from space

scientificamerican.com
15 ポイント·投稿者 akshay326·6 か月前·4 コメント

Show HN: Open-source AI workflows with read-only auth scopes

github.com
12 ポイント·投稿者 akshay326·6 か月前·0 コメント

Show HN: Why delegation beats memory in AI Agents

getseer.dev
1 ポイント·投稿者 akshay326·7 か月前·1 コメント

Show HN: Eval based agent builder (pls roast us)

github.com
1 ポイント·投稿者 akshay326·7 か月前·1 コメント

Cosmic Blast May Be First-Ever Superkilonova Observed

scientificamerican.com
3 ポイント·投稿者 akshay326·7 か月前·0 コメント

コメント

akshay326
·4 か月前·議論
Cloudflare cloned Next.js because the source was right there. Most closed products have 80% of their complexity locked behind auth, encrypted state, and prerequisite flows — you can't reverse-engineer what you can't observe
akshay326
·5 か月前·議論
thanks for shipping gepa! read about it today morning, impressed by its prompt optimization results! PS - the github.io link is truncated
akshay326
·5 か月前·議論
> if you're worried the model is reinforcing your biases..... i agree, i don't understand many domains well enough, yet i feel there's value in calling out assumptions, irrespective of how hard verification is
akshay326
·6 か月前·議論
> Sometimes I go a step further and ask the question with the opposite bias..... curious to try this have you ever found it biasing you in the opposite direction tho?
akshay326
·6 か月前·議論
wow, i wonder how bulletined & concise the outputs of your prompt might be!

have you ever felt this prompt being restrictive in some sense? or found a raw LLM call without this preamble better?
akshay326
·6 か月前·議論
> Have the model play the Devil's advocate. i've tried this sometimes. only issue being dumb me skipping to add similar phrasing every time i open claude or gemini

have you found a way to consistently auto-nudging the model by default?
akshay326
·6 か月前·議論
Ah interesting. i like actor-critic models! do you use it just for coding or non-technical chats too?
akshay326
·6 か月前·議論
> There is an angle for doubt, for sorrow, for hate, for joy, for contemplation, and for devotion.

I’m so intrigued - what was going on inside Hansen's brain?
akshay326
·6 か月前·議論
Dogs?
akshay326
·6 か月前·議論
way outdated but i mumble a few things every now and then -- https://akshay326.com/
akshay326
·6 か月前·議論
What would you cover not-continuous?

Best methods I’ve observed -progressive loading (claude skills) & symbolic search (serena mcp)
akshay326
·6 か月前·議論
trouble self-hosting? checkout our 1-click Railway setup: https://github.com/seer-engg/seer
akshay326
·6 か月前·議論
100% agreed - i think its hard to have both comfort and growth/discomfort at once. for the 'chill' part, you can sandbag and make some money at FMAANG or whatever the new acronym is
akshay326
·6 か月前·議論
This is pretty cool, I wanted to do something with my Readwise Reader too. Jinx today claude code created a 3D Neo4J visualizer tool for YC advice + my quotes collection. Code here - https://github.com/akshay326/quote-viz
akshay326
·6 か月前·議論
I’ve used mini for synthetic dataset generation extensively. Never tried Mistral; will check it out
akshay326
·6 か月前·議論
true both - i've observed i end up spending more tokens + time with linting, than without
akshay326
·6 か月前·議論
which simple models have you found good?
akshay326
·6 か月前·議論
thanks for the idea! https://x.com/akshay326_/status/2009856179854561476
akshay326
·6 か月前·議論
LLMs try to cheat. all sorts of evasive ways or smart tricks in some cases to avoid working on context-heavy tasks. i've constantly observed if left unchecked it tries to loosen the lint settings
akshay326
·6 か月前·議論
thanks i've not used PostToolUse but will checkout. i'm excited about Rust's autofixable issues promise. curious how effective they are, and how deep of a issue can they solve