It's underappreciated how important Google Home could be for agentic use. OpenAI doesnt have that. Apple is busy turning glass to liquid
ChatGPT agent: bridging research and action
201–210 of 508 posts
Re: ChatGPT agent: bridging research and action
#202The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…
People say this, but in my experience it’s not true.
1) The cognitive burden is much lower when the AI can correctly do 90% of the work. Yes, the remaining 10% still takes effort, but your mind has more space for it.
2) For experts who have a clear mental model of the task requirements, it’s generally less effort to fix an almost-correct solution than to invent the entire thing from scratch. The “starting cost” in mental energy to go from a blank page/empty spreadsheet to something useful is significant. (I limit this to experts because I do think you have to have a strong mental framework you can immediately slot the AI output into, in order to be able to quickly spot errors.)
3) Even when the LLM gets it totally wrong, I’ve actually had experiences where a clearly flawed output was still a useful starting point, especially when I’m tired or busy. It nerd-snipes my brain from “I need another cup of coffee before I can even begin thinking about this” to “no you idiot, that’s not how it should be done at all, do this instead…”
Re: ChatGPT agent: bridging research and action
#203It’s like having a junior executive assistant that you know will always make mistakes, so you can’t trust their exact output and agenda. Seems unreliable .
And yet junior exec assistants still get jobs. Must be providing some value.
Re: ChatGPT agent: bridging research and action
#204For me the most interesting example on this page is the sticker gif halfway down the page. Up until now, chatbots haven't really affected the real world for me†. This feels like one of the first moments where LLMs will start affecting the physical world. I type a prompt and something shows up at my doorstep. I wonder how much of the world economy will be driven by LLM-based orders in the next 10 years. † yes I'm awar…
I just want to know what the insurance looks like behind this, lol. An agent mistakenly places an order for 500k instead of 500 stickers at some premium pricing tier above intended one. Sorry, read the fine print, and you're using at your own risk?
Re: ChatGPT agent: bridging research and action
#205I downgraded to Team subscription, I think this is gonna make me upgrade to Pro again.
You just justified their investments.
Re: ChatGPT agent: bridging research and action
#206The security risks with this sound scary. Let's say you give it access to your email and calendar. Now it knows all of your deepest secrets. The linked article acknowledges that prompt injection is a risk for the agent: > Prompt injections are attempts by third parties to manipulate its behavior through malicious instructions that ChatGPT agent may encounter on the web while completing a task. For example, a maliciou…
Anthropic found the simulated blackmail rate of GPT-4.1 in a test scenario was 0.8
https://www.anthropic.com/research/agentic-misalignment
"Agentic misalignment makes it possible for models to act similarly to an insider threat, behaving like a previously-trusted coworker or employee who suddenly begins to operate at odds with a company’s objectives."
Re: ChatGPT agent: bridging research and action
#207The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…
People say this, but in my experience it’s not true. 1) The cognitive burden is much lower when the AI can correctly do 90% of the work. Yes, the remaining 10% still takes effort, but your mind has more space for it. 2) For experts who have a clear mental model of the task requirements, it’s generally less effort to fix an almost-correct solution than to invent the entire thing from scratch. The “starting cost” in me…
>The cognitive burden is much lower when the AI can correctly do 90% of the work. Yes, the remaining 10% still takes effort, but your mind has more space for it.
I think their point is that 10%, 1%, whatever %, the type of problem is a huge headache. In something like a complicated spreadsheet it can quickly become hours of looking for needles in the haystack, a search that wouldn't be necessary if AI didn't get it almost right. In fact it's almost better if it just gets some big chunk wholesale wrong - at least you can quickly identify the issue and do that part yourself, which you would have had to in the first place anyway.
Getting something almost right, no matter how close, can often be worse than not doing it at all. Undoing/correcting mistakes can be more costly as well as labor intensive. "Measure twice cut once" and all that.
I think of how in video production (edits specifically) I can get you often 90% of the way there in about half the time it takes to get it 100%. Those last bits can be exponentially more time consuming (such as an intense color grade or audio repair). The thing is with a spreadsheet like that, you can't accept a B+ or A-. If something is broken, the whole thing is broken. It needs to work more or less 100%. Closing that gap can be a huge process.
I'll stop now as I can tell I'm running a bit in circles lol
Re: ChatGPT agent: bridging research and action
#208The security risks with this sound scary. Let's say you give it access to your email and calendar. Now it knows all of your deepest secrets. The linked article acknowledges that prompt injection is a risk for the agent: > Prompt injections are attempts by third parties to manipulate its behavior through malicious instructions that ChatGPT agent may encounter on the web while completing a task. For example, a maliciou…
There is almost guaranteed going to be an attack along the lines of prompt-injecting a calendar invite. Those things are millions of lines long already, with tones of auto-generated text that nobody reads. Embed your injection in the middle of boring text describing the meeting prerequisites and it's as good as written in a transparent font. Then enjoy exfiltrating your victim's entire calendar and who knows what else.
Re: ChatGPT agent: bridging research and action
#209The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…
> how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... This is where the AI hype bites people. A great use of AI in this situation would be to automate the collection and checking of data. Se…
From John Dewey's Human Nature and Conduct:
“The fallacy in these versions of the same idea is perhaps the most pervasive of all fallacies in philosophy. So common is it that one questions whether it might not be called the philosophical fallacy. It consists in the supposition that whatever is found true under certain conditions may forthwith be asserted universally or without limits and conditions. Because a thirsty man gets satisfaction in drinking water, bliss consists in being drowned. Because the success of any particular struggle is measured by reaching a point of frictionless action, therefore there is such a thing as an all-inclusive end of effortless smooth activity endlessly maintained.
It is forgotten that success is success of a specific effort, and satisfaction the fulfillment of a specific demand, so that success and satisfaction become meaningless when severed from the wants and struggles whose consummations they arc, or when taken universally.”
Re: ChatGPT agent: bridging research and action
#210The "spreadsheet" example video is kind of funny: guy talks about how it normally takes him 4 to 8 hours to put together complicated, data-heavy reports. Now he fires off an agent request, goes to walk his dog, and comes back to a downloadable spreadsheet of dense data, which he pulls up and says "I think it got 98% of the information correct... I just needed to copy / paste a few things. If it can do 90 - 95% of the…
Totally agree.
Also, do you really understand what the numbers in that spreadsheet mean if you have not been participating in pulling them together?