Most active commenters
  • Evidlo(4)

←back to thread

684 points prettyblocks | 16 comments | | HN request time: 0.822s | source | bottom

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
Evidlo ◴[] No.42786869[source]
I have ollama responding to SMS spam texts. I told it to feign interest in whatever the spammer is selling/buying. Each number gets its own persona, like a millennial gymbro or 19th century British gentleman.

http://files.widloski.com/image10%20(1).png

http://files.widloski.com/image11.png

replies(11): >>42786904 #>>42786974 #>>42787151 #>>42787231 #>>42787781 #>>42789419 #>>42789860 #>>42794672 #>>42795730 #>>42795824 #>>42796084 #
1. RVuRnvbM2e ◴[] No.42786904[source]
This is fantastic. How have your hooked up a mobile number to the llm?
replies(2): >>42786967 #>>42786993 #
2. spiritplumber ◴[] No.42786967[source]
For something similar with FB chat, I use Selenium and run it on the same box that the llm is running on. Using multiple personalities is really cool though. I should update mine likewise!
3. Evidlo ◴[] No.42786993[source]
Android app that forwards to a Python service on remote workstation over MQTT. I can make a Show HN if people are interested.
replies(5): >>42787153 #>>42787356 #>>42791613 #>>42791742 #>>42793477 #
4. deadbabe ◴[] No.42787153[source]
I’d love to see that. Could you simulate iMessage?
replies(2): >>42787315 #>>42787660 #
5. Evidlo ◴[] No.42787315{3}[source]
If you mean hook this into iMessage, I don't know. I'm willing to bet it's way harder though because Apple
replies(1): >>42790394 #
6. dkga ◴[] No.42787356[source]
Yes, I'd be interested in that!
7. great_psy ◴[] No.42787660{3}[source]
Yes it’s possible, but it’s not something you can easily scale.

I had a similar project a few years back that used OSX automations and Shortcuts and Python to send a message everyday to a friend. It required you to be signed in to iMessage on your MacBook.

Than was a send operation, the reading of replies is not something I implemented, but I know there is a file somewhere that holds a history of your recent iMessages. So you would have to parse it on file update and that should give you the read operation so you can have a conversation.

Very doable in a few hours unless something dramatic changed with how the messages apps works within the last few years.

replies(1): >>42791450 #
8. dambi0 ◴[] No.42790394{4}[source]
If you are willing to use Apple Shortcuts on iOS it’s pretty easy to add something that will be trigged when a message is received and can call out to a service or even use SSH to do something with the contents, including replying
9. dewey ◴[] No.42791450{4}[source]
They are all in a SQLite db on your disk.
10. potamic ◴[] No.42791613[source]
Why MQTT over HTTP for a low volume, small scale integration?
replies(2): >>42792901 #>>42802009 #
11. sainib ◴[] No.42791742[source]
Interested for sure.
12. c0wb0yc0d3r ◴[] No.42792901{3}[source]
I’m not OP, but I would hazard a guess that those are the tools that OP has at hand.
13. SuperHeavy256 ◴[] No.42793477[source]
I am so SO interested, please make a Show HN
replies(1): >>42796544 #
14. Evidlo ◴[] No.42796544{3}[source]
https://news.ycombinator.com/item?id=42796496
replies(1): >>42796687 #
15. gaudystead ◴[] No.42796687{4}[source]
Sweeeeet, thank you! :)
16. 0xedd ◴[] No.42802009{3}[source]
Good, cheap design that takes care of dead letters vs implementing a failover endpoint that would require extra hardware.

MQTT is plug and play in Python. No more costly than a HTTP server.