HackerTrans
トップ新着トレンドコメント過去質問紹介求人

tgalal

no profile record

投稿

SSH Reverse Prompt Forwarding

tgalal.com
1 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Promptcmd – LLM prompts as CLI progs with args, piping, SSH forwarding

github.com
2 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Templated prompts that travel with you over SSH

github.com
2 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Execute local LLM prompts in remote shells

github.com
2 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Execute local prompts in SSH remote shells

docs.promptcmd.sh
7 ポイント·投稿者 tgalal·4 か月前·2 コメント

Show HN: Execute local prompts in SSH remote shells

docs.promptcmd.sh
4 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Bring your own prompts in SSH remote shells

github.com
1 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Execute local prompts in SSH remote shells

docs.promptcmd.sh
2 ポイント·投稿者 tgalal·4 か月前·0 コメント

Show HN: Bring your own prompts to remote shells

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

Using the BusyBox trick to turn AI prompts into native-looking executables

tgalal.com
1 ポイント·投稿者 tgalal·5 か月前·0 コメント

Show HN: Bashme_a_script_that", generate and cache bash scripts via promptcmd

promptcmd.sh
1 ポイント·投稿者 tgalal·6 か月前·0 コメント

Show HN: READFORME.md

promptcmd.sh
2 ポイント·投稿者 tgalal·6 か月前·0 コメント

Using the BusyBox trick to turn AI prompts into "native" executables

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

Show HN: GenAI Prompts as "Native" Programs

promptcmd.sh
1 ポイント·投稿者 tgalal·6 か月前·0 コメント

Show HN: Promptcmd: AI prompts manager that turns prompts into runnable programs

promptcmd.sh
4 ポイント·投稿者 tgalal·6 か月前·1 コメント

コメント

tgalal
·4 か月前·議論
> The server does see the audio during processing (that's how GPU transcription works), but the final stored transcript is encrypted with a key derived from your password that never leaves your browser.

You conveniently omit mentioning that the server also sees the transcript before returning it to the client side browser. Whether it is "immediately" erased, is something the client must trust the server to do. You might as well save yourself the roundtrip by encrypting server side, returning the key, then deleting it, same outcome.
tgalal
·4 か月前·議論
Every time I see the term "Zero knowledge encryption" something dies inside of me, as "Zero Knowledge" is not a property of ciphertexts but proofs. But this has seriously taken things up a notch: the server learns both plaintext audio and and transcripts. So that's literally "full knowledge" encryption.

Just drop encryption altogether, the server is trusted anyway. It adds absolutely no guarantees on anything than without the way encryption is currently performed.
tgalal
·4 か月前·議論
[dead]
tgalal
·4 か月前·議論
The point is to avoid installing tools or granting LLM access and the "steering wheel" on the server itself. The data you pipe is the same data you'd copy-paste into ChatGPT or similars anyway. There is certainly bit of latency when piping/reading a lot of of data into the context, as everything is tunneled through the local machine, but I'd argue that the context size being limited by the llm itself makes it acceptable for most use cases.
tgalal
·4 か月前·議論
I wanted a "seamless" way for executing llm prompts in my terminal for recurring tasks, and came up with this:

http://github.com/tgalal/promptcmd

The cool thing about it is that it also works over remote ssh shells, so quite handy in managing my homelab.
tgalal
·6 か月前·議論
Hi HN, I’m the author.

I built promptcmd because I thought prompts can be neatly integrated into CLI and look like familiar commands, rather than being run "via a tool" (explicitly).

promptcmd lets you define prompts as files, compose them, and run them like native commands.

Happy to answer questions, especially around design tradeoffs or missing features.