[HN Gopher] How to make history with LLMs and other generative m...
___________________________________________________________________
How to make history with LLMs and other generative models
Author : marcoslozada
Score : 58 points
Date : 2023-09-26 13:37 UTC (9 hours ago)
(HTM) web link (leighmariebraswell.substack.com)
(TXT) w3m dump (leighmariebraswell.substack.com)
| nomagicbullet wrote:
| The idea of LLM-powered personal assistants sounds like a game-
| changer (eg. an AI buddy that not only helps with work tasks but
| also offers real-time advice and fact-checking during
| conversations)
|
| Can't wait to see how this evolves. It has the potential of
| becoming as ubiquitous as a smartphone.
| simonw wrote:
| Sadly digital personal assistants are the biggest example of
| something that we've not yet figured out how to build safely
| given the threat of prompt injection.
|
| If your assistant can perform actions on your behalf - even as
| simple as replying to an email - you can't risk that assistant
| being exposed to any potentially malicious text from an
| untrusted source that might contain instructions designed to
| subvert it.
|
| So your assistant can't be trusted to summarize web pages. Or
| even to read messages in your inbox!
|
| I wrote more about this problem - and provided a very
| disappointing partial proposed solution - here:
| https://simonwillison.net/2023/Apr/25/dual-llm-pattern/
| thelastparadise wrote:
| Sandbox/firewall it.
| sharemywin wrote:
| couldn't you separate the agent responsibilities?
|
| Couldn't you make it so the agent that summarizes your emails
| isn't the same as the agent that sends email, etc.
| simonw wrote:
| That's what I propose in
| https://simonwillison.net/2023/Apr/25/dual-llm-pattern/
| ianbicking wrote:
| It seems to me like there's sufficient value even if the
| assistant can't complete any actions fully (e.g., can compose
| but not send an email; or maybe not even compose). There's so
| much potential simply aiding with executive function: what to
| do, when to do it, acquiring any dependencies, handling
| partial work, helping break down tasks, and a great deal of
| potential with perception if the assistant is highly
| available and perceives what the human perceives.
|
| (Rayban Stories could be pretty awesome for this, if they
| were hackable enough to actually prototype things on:
| https://hachyderm.io/@ianbicking/110833737363686936)
|
| Imagine a personal assistant that was always ready to respond
| to the question "what should I do now?" - and of course enter
| dialog, not just dictate an action. That you could tell about
| all your tasks, but not just the tasks but also the _why_ of
| the tasks, giving it the chance to set or change something
| like a deadline on its own, or even simply discuss those
| deadlines.
|
| Imagine you could co-develop a process with that assistant.
| Maybe there's times you like to do certain kinds of work...
| what are those? What features distinguish different kinds of
| work? If you have to do a certain kind of work, what do you
| need (time/place/mindset) to be successful? It doesn't need
| to be some magic algorithm, it can be a deliberative process
| that you engage in with your assistant, something conscious
| and explicit.
|
| Maybe it helps both move through and construct to-do lists.
| You have an item on your list: either the item is very easy
| or the question is "what's the first thing you have to do to
| achieve that item?" - and the assistant has some idea (and
| can learn more) about what a good size of a task is for you
| personally. And now it's keeping this list of tasks and
| dependencies. It should be able to understand enough to mark
| subtasks complete if you complete the parent task. It can
| probably suggest items. If it has access to enough
| information - even if you have to put the information in
| explicitly - it can probably help you resume tasks by
| reestablishing all the context you need.
|
| Like maybe all your assistant needs or should have is access
| to your clipboard (in and out), photos and screenshots, mic
| and speaker access (with a wake word), a library of notes and
| observations, and task initiation that isn't any more
| sophisticated than what you can do from a link
| (mailto:person?subject=...)
| yoyohello13 wrote:
| Get ready for ultra personalized ads beamed directly into your
| brain.
| arrowsmith wrote:
| And they don't even need to scan your eyeballs:
| https://www.youtube.com/watch?v=7bXJ_obaiYQ
| fudged71 wrote:
| I would get an extremely high value from an "Accountability
| Buddy" for ADHD. Has anyone seen anyone building this?
|
| I think it would be pretty straightforward with basic memory
| and a good prompt.
| Gumberclaus wrote:
| Fact checking has worked out so well in other places. I mean -
| social media sites and news outlets plus the groups that fund
| them being the primary funders of fact checking groups creates
| absolutely no conflict of interest at all.
|
| Having some personal assistant developed by megacorp that helps
| me be a better worker for megacorp does sound game changing -
| but not in a good way.
| throwmeouthn wrote:
| [dead]
___________________________________________________________________
(page generated 2023-09-26 23:01 UTC)