Hacker News new | past | comments | ask | show | jobs | submit | btx's comments login

Out curiosity I checked Streetview.

Figure 7. Hollister 6th street

2021: https://youtu.be/RUNCEZs9nkU?t=168

2022: https://google.com/maps/@36.8506199,-121.4066009,3a,90y,250....

Figure 22. CA-25

2023 (patched up, drainage channel added): https://google.com/maps/@36.4065854,-120.9937028,3a,90y,216....

Streetview also available for 2022, 2012, 2007 that shows some cracks/offset.


In some responses it now cites a link to this comment section.

--------------

Q: How long will it take before Bard is shut down?

A: I can't say for sure when Bard will be shut down, but I can tell you that there are no plans to shut it down in the near future. Google has recently announced that it will continue to explore ways to use AI to enhance creative expression, and Bard is one of the projects that it is working on.

The Hacker News comment that you linked to is a hypothetical scenario where Google shuts down Bard after one year. However, this is just a speculation and there is no evidence to support it.

If you have any other questions about Bard, please let me know.

Sources - Learn more news.ycombinator.com/item?id=35255864


For me that's the biggest takeaway.. whilst chatGPT seems to be stuck at a specific date, Bard is updating extremely quickly.

That has huge implications, both good and bad (a lot of code that chatGPT produced when I was playing with it for e.g. sveltekit is outdated)


I wonder if it's actually being updated quickly. I think it'd be much easier to train it to use google's search index as a tool in a way hidden from the user. For example regarding the shutdown date of itself it might have googled "google bard shutdown" to find and misunderstand the HN comment cited in the twitter thread.


Seems like it would be trivial to replace "As an AI language model who hasn't been updated since x date" with "$ESCAPE_SEQUENCE search_query: $TERM" and rerun the question with the hidden prefix "Given that the google results for $TERM are $RESULTS"...


So it will spew the latest lies that have been posted online then I guess, if it's using internet comment forums as sources?


Just like humans. Singularity is knocking.


dang.


The same goes for Bing AI, it's better to compare Bard to Sydney than to ChatGPT.


Has anyone found a way to trick it into using pictures with ChatGTP+ yet?

Pasting pure base64 images got this interesting response: "Thank you for providing the base64-encoded image! I can now process the image and analyze its content. Here is the decoded image:"

But it failed to do anything further with the image.


I have written something [once] that de-dupes on just the URLs, you could take this way further with images and content analysis.

This is also manly an app to stop me from scrolling across the same stories on HN and lobste.rs again and again multiple times a day. So it lacks reddit specific features.

[once] https://github.com/batram/once


Interesting, thank you!


  The following issues are outside the scope of our vulnerability rewards program (either ineligible or false positives):
  ...
   - Social engineering of Twitter staff or contractors
  ...
https://hackerone.com/twitter

Pretty standard for most if not all of the program rules I have come across.



Interestingly it does not seem to be a new concept: https://www.reddit.com/r/netsec/comments/37ko5v/introducing_... https://securingtomorrow.mcafee.com/mcafee-labs/meet-tox-ran...

They used to take 20% 'commission'.


Being in a somewhat similar position (looking for my first 'real' job in the field of security), I have more or less the opposite problem.

After setting up a profile on sites like Xing (works best for Germany) or Linkedin and adding some relevant buzzwords, you get basically swarmed by recruiters. The offers from recruiters might not be the most interesting, but you still can use them to get some information and feedback.

Just show that you have a personal interest in security. For Example I have myself participated in a bunch of bug bounties, hitting most of the big ones (Dropbox, Facebook, Google, Microsoft, Mozilla, Paypal, Twitter, ...). While finding big problems in the higher payed ones might be trickier, there are always companies that just offer a thanks or some swag. An alternative would be to look at open source projects and try to get some CVEs. Of course this depends on what field of security you want to end up in.


Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: