Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

arxiv.org

Post reply on HN
Print view View original

21–30 of 280 posts

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#21

Post by avereveard »

quonn wrote: post #7
catchnear4321 wrote: post #6

Earlier quoted context omitted.

Being terrified doesn’t serve much purpose at this point. We are going too fast. Have been for years. This is just the first clear indication. Braking is fatal, but some seem pretty hell-bent. Deceleration is complicated, and it seems highly unlikely that there would be sufficient consensus for true deceleration. Local deceleration is simply waiting for the acceleration occurring somewhere else to overcome your effor…

I disagree. ChatGPT is a clear turning point. We have not been going too fast before, at least not outside LLMs. Singularity is a belief system, it has very little to do with AI. edit: I also think if we would ever get to a point where AI gets close to a point of possibly getting out of control as you imply it would simply be banned in the US/Canada/EU/Australia. Furthermore Latin America and Africa could and would b…

Gpt plus langchain agents is quite scary

It will use every tool you give it to reach the goal you give him. It will try forever if needed.

I bet state actor are already plugging in tooling to register social account and automate credible propaganda. Maybe not with gpt itself, but privately hosted fine tuned models.

This can win elections.

You can plug wordpress and build infinite blogs with infinite post with the unique scope of building mass around a topic.

This can alter Wikipedia, many people don't ever check sources and take it at face value.

You can not only build fake research paper, but fake the whole research team and their whole interactions with the community and investor.

This can fraud millions.

Tools enable this today.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#22

Post by Imnimo »

Why are the example outputs in the Figures ungrammatical?

>A text can describe the given image: a herd of giraffes and zebras grazing in a fields. In addition, there are five detected objects as giraffe with score 99.9%, zebra with score 99.7%, zebra with 99.9%, giraffe with score 97.1% and zebra with score 99.8%. I have generated bounding boxes as above image. I performed image classification, object detection and image captain on this image. Combining the predictions of nlpconnet/vit-gpt2-imagecaptioning, facebook/detr-resnet-101 and google/vit models, I get the results for you.

Is it just that the in-context demonstrations are also ungrammatical and ChatGPT is copying them? It feels very unlike the way ChatGPT usually writes.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#23

Post by _yb2s »

basch wrote: post #20
_yb2s wrote: post #19

Earlier quoted context omitted.

I agree, I suspect AGI is possible right now with a similar system only slightly more sophisticated than this one. The right "glue" for existing models, and plugins to existing data sources all coordinated in a system. GTP-4 would do the managing, and handling, and some simple template API and handler script would allow it to call instances of itself or other models, track recursion depth, and automatically remind GT…

It also, in my pay opinion, needs a memory store. I need to be able to save something to a variable and call back that exact variable. Right now, because it’s just pure text input of the whole conversation, it can forget or corrupt it’s “memory”. Even something like writing a movie script doesn’t work if it constantly forgets characters names or settings or plot points.

My description above includes a memory store. It is a single variable that it can save and recover, and will automatically get sent back to it at regular intervals if it forgets it saved anything. Only a single text string variable is needed, as GTP-4 is smart enough to realize it can compress, pickle, etc. as many things as it needs into that.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#24

Post by zoba »

These sort of agent-architecture AIs are where I think things will head and also where things will get more dangerous.

When an AI has a goal and an ability to break the goal down, and make progress towards the goal… the only thing stopping the AI from misalignment is whatever it’s creator has specified as the goal.

Things get even more tricky when the agent can take in new information and deprioritize goals.

I have been curious why OpenAI haven’t discussed Agent-based AIs.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#25

Post by blibble »

quonn wrote: post #16
blibble wrote: post #14

Earlier quoted context omitted.

what do the owners of production do when the 6 billion workers decide they don't like not being able to eat?

I wonder if the physical workers join especially for services. Perhaps not, since they may be needed.

so bring it down to 3 billion people who know how to find datacentres on google maps

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#26

Post by roflyear »

Workaccount2 wrote: post #8

I strongly suspect the first AGI will come sooner than expected on the back of a "glue" AI that can intelligently bond together a web of narrow AIs and utilities. I got access to the wolfram plugin for chatGPT, and it turned it from a math dummy to a math genius overnight. A small step for sure, but a hint of what's to come.

Except, whatever model is doing the orchestration will still not "understand" the problem (be able to learn from new information provided).

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#28

Post by _yb2s »

roflyear wrote: post #26
Workaccount2 wrote: post #8

I strongly suspect the first AGI will come sooner than expected on the back of a "glue" AI that can intelligently bond together a web of narrow AIs and utilities. I got access to the wolfram plugin for chatGPT, and it turned it from a math dummy to a math genius overnight. A small step for sure, but a hint of what's to come.

Except, whatever model is doing the orchestration will still not "understand" the problem (be able to learn from new information provided).

GPT-4 can do this. I realize that a description of how these models work implies that this is absolutely impossible, so I have no explanation other than suggesting you go try it out for yourself.

Re: HuggingGPT: Solving AI tasks with ChatGPT and its friends in HuggingFace

#29

Post by brotchie »

_yb2s wrote: post #19
Workaccount2 wrote: post #8

I strongly suspect the first AGI will come sooner than expected on the back of a "glue" AI that can intelligently bond together a web of narrow AIs and utilities. I got access to the wolfram plugin for chatGPT, and it turned it from a math dummy to a math genius overnight. A small step for sure, but a hint of what's to come.

I agree, I suspect AGI is possible right now with a similar system only slightly more sophisticated than this one. The right "glue" for existing models, and plugins to existing data sources all coordinated in a system. GTP-4 would do the managing, and handling, and some simple template API and handler script would allow it to call instances of itself or other models, track recursion depth, and automatically remind GT…

Yep, the tipping point for me was seeing a demo of GPT-4 writing code, then being shown exceptions where the code failed, and successfully fixing the code given that feedback.

Seems that for any task where you can generate an error signal with some information ("ok, what you just tried to do didn't succeed, here's some information about why it didn't succeed"), GPT-4 can generally handle this information to fix the error, and or seek out more information via tools to move forward on a task.

Only thing that's really missing is somebody to crack the back of a memory module (perhaps some trick with embeddings and a vector db) is all it takes for this to be AGI.

Post reply on HN