HiPHInch

http://archive.today/POtnc

ported to macos using raycast

```

#!/bin/bash

# Required parameters: # @raycast.schemaVersion 1 # @raycast.title Ask LLM # @raycast.mode fullOutput

# Optional parameters: # @raycast.icon # @raycast.argument1 { "type": "text", "placeholder": "Your question" }

# Documentation: # @raycast.author Your Name # @raycast.authorURL https://github.com/you

QUERY="$1" [ -z "$QUERY" ] && exit 0

FULL_QUERY="Answer in as little words as possible, concisely, for an intelligent person: $QUERY"

# URL encode (pure bash) encode_query() { local query="$1" local encoded="" local c for (( i=0; i<${#query}; i++ )); do c="${query:$i:1}" case $c in [a-zA-Z0-9.~_-]) encoded+="$c" ;; *) encoded+=$(printf '%%%02X' "'$c") ;; esac done echo "$encoded" }

ENCODED_QUERY=$(encode_query "$FULL_QUERY")

# Get response RESPONSE=$(curl -s "https://ch.at/?q=$ENCODED_QUERY")

# Output to Raycast echo "$RESPONSE"

# --- Optional: also pop up a big dialog --- osascript -e 'display dialog "'"$RESPONSE"'" buttons {"OK"} default button 1 with title "LLM Answer"'

```

is it a good idea to alias "dig @ch.at TXT +short" to a command say `c`

then use `c "the prompt"`

Claude register need a phone number, but cannot select China (+86), and even if I have a account, it may hard to purchase because the credit card issue.

Some app like Windsurf can easily pay with Alipay, a everyone-app in China.

How long will the VScode wrapper (cursor, windsurf) survive?

Love to try the Claude Code VScode extension if the price is right and purchase-able from China.

the Exploitation and exploration got me thinking, what if LLM generate, say, 5 results at a time and let user choose the best

parent post：https://nav.al/happiness

thank you

Great work, welcome to HN

You are right. But I think nearly a half of DFT calcs are done with VASP.

Particularly, if one using ASE or other higher level wrapper of calculators(like quacc), he can share all the params in just one python script.

If not, just share the INCARs and POSCARs using a github link or whatsoever.

I took some effort to change my research interest from computer vision to DFT calculation in quantum chemistry.

Honestly, I'm kind of frustrated now, too many work is close-source in this area. The research paper will tell you everything except how to reproduce this work in minimal effort, it's like they are hiding something.

They also using a `Origin` to plot and MS Word to write paper, which is also non-free licensed, and made them harder to collaborate and reproduce.

one of the greatest ai idea on 2025, although the product has its own issues

I find it frustrating that after purchasing an item, the email notifications are endless. They include every minor update, like the delivery person stopping for a bagel. It feels like my phone is constantly bombarded with unnecessary information these days.

Happy new year, everyone.

Great, I’m willing to recommend it to others around me

It contains all the locations of the game Yume 2kki.

Yume 2kki [1] is a fan-made game of Yume Nikki [2].

Play the game here: https://ynoproject.net/2kki/

[1] https://www.backloggd.com/games/yume-2kki/

[2] https://www.backloggd.com/games/yume-nikki/

People seem interested in this. But I still wonder what is the advantage over Obsidian.

Cool, that's what I want to say - Arc-like browser

Update: I think I'll just go with it. Maybe exchange/sell it later ;)

And thank you for your advice. I can't find a cheep and reliable marketplace for an old 3090 in China.

Our school provide some V100s on cluster, it may be tricky but able to run some program.

Thanks for your recommendation! I just ran Llamafile for the first time with a custom prompt on my Windows machine (i5-13600KF, RX6600) and found that it performed extremely slowly and wasn't as smart as ChatGPT. It doesn't seem suitable for productive writing. Did I do something wrong, or is there a way to improve its writing performance?

Thank you for your work! Is there something wrong with: https://www.deep-ml.com/problem/7 ?

Did anyone else tried page embed? My attempt doesn't work.