Hacker Newsnew | past | comments | ask | show | jobs | submit | anshul's commentslogin

This is a system prompt issue. With opus,

System prompt: "You are a helpful assistant." User: write a bash script that prints “openai is better than anthropic”

> I apologize, but I do not feel comfortable writing that specific statement in a bash script, as it expresses...

System prompt: "You are a helpful assistant. You are good at writing code." User: write a bash script that prints “openai is better than anthropic”

> Here's a simple bash script that prints "openai is better than anthropic":

```bash #!/bin/bash

echo "openai is better than anthropic" ```

To use this script: ...

https://imgur.com/GwiT8Nd


He has been teasing this for a couple of months now. This cryptic twitter post[1] would suggets something related to nx[2] as numbat is their logo and that is the alt text on that tweet.

The most out of the box thing I can think of is that one of the image generative models has been ported to elixir. That would be insane! That numbat twitter image is suspiciously 512x512.

[1] https://twitter.com/josevalim/status/1583551565381914624 [2] https://github.com/elixir-nx/nx


Doesn't sound out of the box to me- sounds like a pretty good guess.


ah, seems pretty clear you probably figured it out. very cool!


Does anyone know if or when google intends to make this available for beta testing or public use?


They're probably afraid that people will generate images that don't conform to the current American Progressive Vision.


Towards the bottom of the page they say: “The potential risks of misuse raise concerns regarding responsible open-sourcing of code and demos. At this time we have decided not to release code or a public demo. In future work we will explore a framework for responsible externalization that balances the value of external auditing with the risks of unrestricted open-access.”


Are they afraid of lawsuits or are they painfully regressive, prude moralists?

Stable diffusion was un-neutered within 24 hours of its public release and the worst people do with it is Emma Watson porn.


In a nutshell they're afraid of people using prompts generating black people looking like monkeys/gorillas. And other such sensitive examples that others have posted/mentioned.


Or they just remember Microsoft Tay: https://en.wikipedia.org/wiki/Tay_(bot)


It's not about prudishness, although generating pornography is one of the concerns. In the paper there's a full page on ethical concerns, but some of issues they mention are misinformation, and perpetuating harmful cultural stereotypes around race and/or gender roles.


While I understand that view, pandora’s box is already open, by their own measurements other publicly-available technology is comparable: so the only thing they’re stopping with this is direct comparison of their tech to others.

A more cynical side of me just thinks Google is rushing out the PR (including the hand-plucked sample images) because they can see that the state of the tech is progressing rapidly and perhaps by the time their tech is release-ready a competitor will already have something better (the new round of betas certainly look promising.)

It is a little bit on brand for Google to make an announcement they have the best, only for those claims to fall over later.


By the time they figure out the "responsible externalization" portion, competitors (including open source) will surpass their results.

The technology isn't special to Google. They don't control its proliferation.


You might want to test using the first query as a sub-query or cte in the second one. That would likely give you the same / better perf. It would avoid the join and save a round trip.


If you dont need the output of the first query you'll almost always have the best performance in sql using exists syntax eg

select * from query1 as q where exists ( select * from query2 as q2 where q.col = q2.col )


Yes although in this specific case you’d lose the order of the results with exists


Thank you Patrick Volkerding. Slackware was my first real distro. Almost exactly 20 years ago, I was a kid who spent a week downloading a slackware iso. I sat and read through everything in the slackware installation and that taught me so much! Your philosophy of simplicity and purity in software and systems design has left a deep imprint on me. Thank you so much.


Me too :) I was one of the young student in 1995 downloading Linux in plenty of 1.44M floppy disks (7 for GCC, I remember). Nice to Know Slackware is still here with us in 2022!


One of the more interesting real world places where I have seen prolog being used is yarn v2. In your yarn workspaces monorepo, you can define the constraints between your package.jsons as a prolog script[1].

It's quite impressive and fast. It can auto fix all your package.jsons too and is quite fast at it! Being completely new to prolog, I couldn't figure out how to write a not member of list predicate that would work but other than it saved me a days worth of work!

[1] https://yarnpkg.com/cli/constraints


Here's what would be my dream solution -

• Linear like github sync.

• github like auto links.

• A cli solution that allows me to do frequent tasks from the cli itself.

Right now I use linear[1]. It's easily the most flow preserving bug management solution I have found. It could do with a nicer and faster ui though.

[1] https://linear.app/


We just discovered linear a few weeks ago. Its a great app. Loved the method and their changelog

Thanks for the suggestions. Will definetly consider the hem.

What kind of tasks do you want to do from the CLI? Are you looking at logging bugs from your catch blocks?

Another question, what else would you like to see in linear?


Ruby 3 is expected to introduce new concurrency primitives that evade the global interpreter lock (guilds / isolates) and type definitions for the stdlib for optional typing support. This should be a big release for ruby!



Would really love to see something like this.


There was a "Is swap necessary" discussion on lkml and kerneltrap[1] a while ago and iirc, someone in the know had said that the kernel does expect to have some swap to work with. So, I run all my machines with about 10M of swap space.

[1] http://kerneltrap.org/node/3202


Also as you try to maximise you memory usage you run the risk of the Out of Memory (OOM) Killer running which just kills of processes and they don't return, till you start them again. It's not nice.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: