Ask HN: Is anyone doing anything cool with tiny language models?

Re:Ask HN: Is anyone doing anything cool with tiny language ... by kreyenborgi on Wednesday January 22, 2025 @02:51AM (#42790197)

I read it the other way, their code contains eg fetch(url, pw:hunter123), and they're asking Claude anonymized questions like "implement handler for fetch(url, {pw:mycleartrxtpw})"

And then claude replies

fetch(url, {pw:mycleartrxtpw}).then(writething)

And then the local llm converts the placeholder mycleartrxtpw into hunter123 using its access to the real code

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by sundarurfriend on Wednesday January 22, 2025 @08:04AM (#42792369)

> Put in all your work related questions in the plugin, an LLM will make it as an abstract question for you to preview and send it

So the LLM does both the anonymization into placeholders and then later the replacing of the placeholders too. Calling the latter step de-anonymization is confusing though, it's "de-anonymizing" yourself to yourself. And the overall purpose of the plugin is to anonymize OP to Claude, so to me at least that makes the whole thing clearer.

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by mettamage on Wednesday January 22, 2025 @09:58AM (#42793493)

I could've been a bit more clear, sorry about that.

[ Parent | on HN ]

Re:Ask HN: Is anyone doing anything cool with tiny language ... by mettamage on Wednesday January 22, 2025 @09:55AM (#42793460)

It's that yea

Flow would be:

1. Llama prompt: write a console log statement with my username and password: mettamage, superdupersecret

2. Claude prompt (edited by Llama): write a console log statement with my username and password: asdfhjk, sdjkfa

3. Claude replies: console.log('asdfhjk', 'sdjkfa')

4. Llama gets that input and replies to me: console.log('mettamage', 'superdupersecret')

[ Parent | on HN ]