Comments URL: https://news.ycombinator.com/item?id=47791179

Points: 2

# Comments: 0

Do we just become “watchers” who wait for results? Should we be monitoring them closely, or is it better to step away and do something else—like reading, watching a lecture, or even playing games—while the agents run?

For people who use coding agents regularly: what’s your workflow? How do you stay productive without hovering, and how do you decide when to intervene?

Comments URL: https://news.ycombinator.com/item?id=46753695

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46588929

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45719788

Points: 332

# Comments: 185

Comments URL: https://news.ycombinator.com/item?id=45320715

Points: 30

# Comments: 4

```

#!/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"'

```

then use `c "the prompt"`

Comments URL: https://news.ycombinator.com/item?id=44440190

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44315841

Points: 7

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44188839

Points: 254

# Comments: 122

1. Cursor and Windsurf

   - Both work nicely on local, but they use token-saving strategies:

     - With very long context, they may truncate important information, causing the suggested code to miss key details.

     - Even in normal scenarios, complex cases might exceed context or quota limits, interrupting suggestions.

   - Directly calling paid APIs (e.g., OpenAI’s ChatGPT/GPT-4 API) works well but is expensive.

   - Some free or community APIs (open-source mirrors, community editions) can be unstable, rate-limited, or slow.

   - Many recommend its ability to rewrite, refactor, generate tests, etc., but for simple code completion, its cost-performance ratio may be lower than some smaller vendors or open-source plugins.

   - Listed at the top on SWE Bench, it claims to support code refactoring, generating comments via LLMs, batch rewrites, and more.

   - However, it seems rarely discussed in developer circles. How well does it support?

- Which LLM-assisted coding tool are you currently using? (IDE plugin, standalone client, or API-based)

- What are the main reasons for choosing it? (e.g., cost, response speed, context length support, feature set, etc.)

- What pros and cons have you encountered during actual development? Specifically, how does it perform for debugging, refactoring, generating unit tests, automatic bug fixes, etc.?

- If you have switched tools before, why did you switch?

Thank you for sharing your experiences!

Comments URL: https://news.ycombinator.com/item?id=44160270

Points: 11

# Comments: 4

Comments URL: https://news.ycombinator.com/item?id=44085744

Points: 3

# Comments: 0

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

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

Comments URL: https://news.ycombinator.com/item?id=43991938

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=43679943

Points: 21

# Comments: 5