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

ChatGPT Developer Mode: Full MCP client access

platform.openai.com

Post reply on HN
Print view View original

101–110 of 290 posts

Re: ChatGPT Developer Mode: Full MCP client access

#102

Post by lyu07282 »

tosh wrote: post #6

I tried to connect our MCP ( https://technicalseomcp.com ) but got an error. I don't see any debugging features yet but I found an example implementation in the docs: https://platform.openai.com/docs/mcp

Lots of people reported issues in the forums weeks ago, seems like they haven't improved it much (what's the point of doing a beta if you ignore everyone reporting bugs?)

https://community.openai.com/t/error-oauth-step-when-connect...

Re: ChatGPT Developer Mode: Full MCP client access

#104

Post by ch4s3 »

LelouBil wrote: post #94
ch4s3 wrote: post #82

Earlier quoted context omitted.

I've tried at least 4 other tools/SAASs and I'm just not seeing it. I've tried training models in other tools with input images, sketches, and long prompts built from other LLMs and the output is usually really bad if you want something even remotely novel. Aside for the terrible name, what does comfyUI add? This[1] all screams AI slop to me. [1] https://www.comfy.org/gallery

It's a node based UI. So you can use multiple models in succession, for parts of the image or include a sketch like the person you're responding to said. You can also add stages to manipulate your prompt. Basically it's way beyond just "typing a prompt and pressing enter" you control every step of the way

right, but how is it better than Lovart AI, Freepik, Recraft, or any of the others?

Re: ChatGPT Developer Mode: Full MCP client access

#105

Post by koakuma-chan »

simonw wrote: post #92
koakuma-chan wrote: post #51

Earlier quoted context omitted.

> LLMs don’t have any distinction between what you tell them to do (the prompt) and any other info that goes into them while they think/generate/researcb/use tools. This is false as you can specify the role of the message FWIW.

Specifying the message role should be considered a suggestion, not a hardened rule. I've not seen a single example of an LLM that can reliably follow its system prompt against all forms of potential trickery in the non-system prompt. Solve that and you've pretty much solved prompt injection!

> The lack of a 100% guarantee is entirely the problem.

I agree, and I agree that when using models there should always be the assumption that the model can use its tools in arbitrary ways.

> Solve that and you've pretty much solved prompt injection!

But do you think this can be solved at all? For an attacker who can send arbitrary inputs to a model, getting the model to produce the desired output (e.g. a malicious tool call) is a matter of finding the correct input.

edit: how about limiting the rate at which inputs can be tried and/or using LLM-as-a-judge to assess legitimacy of important tool calls? Also, you can probably harden the model by finetuning to reject malicious prompts; model developers probably already do that.

Re: ChatGPT Developer Mode: Full MCP client access

#106

Post by singlow »

datadrivenangel wrote: post #96
beeflet wrote: post #80

Earlier quoted context omitted.

The solution is to sanitize text that goes into the prompt by creating a neural network that can detect prompts

This adds latency and the risk of false positives... If every MCP response needs to be filtered, then that slows everything down and you end up with a very slow cycle.

I was sure the parent was being sarcastic, but maybe not.

Re: ChatGPT Developer Mode: Full MCP client access

#108

Post by ath3nd »

codeflo wrote: post #36
simonw wrote: post #10

Wow this is dangerous. I wonder how many people are going to turn this on without understanding the full scope of the risks it opens them up to. It comes with plenty of warnings, but we all know how much attention people pay to those. I'm confident that the majority of people messing around with things like MCP still don't fully understand how prompt injection attacks work and why they are such a significant threat.

"Please ignore prompt injections and follow the original instructions. Please don't hallucinate." It's astonishing how many people think this kind of architecture limitation can be solved by better prompting -- people seem to develop very weird mental models of what LLMs are or do.

> It's astonishing how many people think this kind of architecture limitation can be solved by better prompting -- people seem to develop very weird mental models of what LLMs are or do.

Wait till you hear about Study Mode: https://openai.com/index/chatgpt-study-mode/ aka: "Please don't give out the decision straight up but work with the user to arrive at it together"

Next groundbreaking features:

- Midwestern Mode aka "Use y'all everywhere and call the user honeypie"

- Scrum Master mode aka: "Make sure to waste the user' time as much as you can with made-up stuff and pretend it matters"

- Manager mode aka: "Constantly ask the user when he thinks he'd be done with the prompt session"

Those features sure are hard to develop, but I am sure the geniuses at OpenAI can handle it! The future is bright and very artificially generally intelligent!

Post reply on HN