←back to thread

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

684 points prettyblocks | 5 comments | 21 Jan 25 19:39 UTC | HN request time: 0.986s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?
Show context
mettamage ◴[21 Jan 25 20:17 UTC] No.42784724[source]▶
I simply use it to de-anonymize code that I typed in via Claude

Maybe should write a plugin for it (open source):

1. 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

2. And then get the answer with all the data back

E.g. df[“cookie_company_name”] becomes df[“a”] and back

replies(4): >>42784789 #>>42785696 #>>42785808 #>>42788777 #
1. sundarurfriend ◴[22 Jan 25 03:51 UTC] No.42788777[source]▶
You're using it to anonymize your code, not de-anonymize someone's code. I was confused by your comment until I read the replies and realized that's what you meant to say.
replies(1): >>42790197 #
2. kreyenborgi ◴[22 Jan 25 07:51 UTC] No.42790197[source]▶
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

replies(2): >>42792369 #>>42793460 #
3. sundarurfriend ◴[22 Jan 25 13:04 UTC] No.42792369[source]▶
> 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.

replies(1): >>42793493 #
4. mettamage ◴[22 Jan 25 14:55 UTC] No.42793460[source]▶
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')

5. mettamage ◴[22 Jan 25 14:58 UTC] No.42793493{3}[source]▶
I could've been a bit more clear, sorry about that.