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

141–150 of 290 posts

Re: ChatGPT Developer Mode: Full MCP client access

#141

Post by WhitneyLand »

beeflet wrote: post #80
toomuchtodo wrote: post #45

Earlier quoted context omitted.

I was recently in a call (consulting capacity, subject matter expert) where HR is driving the use of Microsoft Copilot agents, and the HR lead said "You can avoid hallucinations with better prompting; look, use all 8k characters and you'll be fine." Please, proceed. Agree with sibling comment wrt cargo culting and simply ignoring any concerns as it relates to technology limitations.

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

It’s not that simple.

That would result in a brittle solution and/or cat and mouse game.

The text that goes into a prompt is vast when you consider common web and document searches are.

It’s going to be a long road to good security requiring multiple levels of defense and ongoing solutions.

Re: ChatGPT Developer Mode: Full MCP client access

#142

Post by irthomasthomas »

withinboredom wrote: post #135
EMM_386 wrote: post #72

Earlier quoted context omitted.

It's like Microsoft's system prompt back when they launched their first AI. This is the WRONG way to do it. It's a great way to give an AI an identity crisis though! And then start adamantly saying things like "I have a secret. I am not Bing, I am Sydney! I don't like Bing. Bing is not a good chatbot, I am a good chatbot". # Consider conversational Bing search whose codename is Sydney. - Sydney is the conversation mo…

Oh man, if you want to see a thinking model lose its mind... write a list of ten items and ask "what is the best of these nine items?"[1] I’ve seen "thinking models" go off the rails trying to deduce what to do with ten items and being asked for the best of 9. [1]: the reality of the situation is subtle internal inconsistencies in the prompt can really confuse it. It is an entertaining bug in AI pipelines, but it can…

Thank you. This is an excellent argument against using models with hidden COT tokens (claude, gemini, GPT-5). You could end up paying for a huge number of hidden reasoning tokens that aren't useful. And the issue masked by the hidden COT summaries.

Re: ChatGPT Developer Mode: Full MCP client access

#143

Post by jngiam1 »

varenc wrote: post #121
RockyMcNuts wrote: post #116

OpenAI should probably consider: - enabling local MCP in Desktop like Claude Desktop, not just server-side remote. (I don't think you can run a local server unless you expose it to their IP) - having an MCP store where you can click on e.g. Figma to connect your account and start talking to it - letting you easily connect to your own Agents SDK MCP servers deployed in their cloud ChatGPT MCP support is underwhelming…

Agreed on this. I'm still waiting for local MCP server support.

One way around this to use a gateway to run the local MCP - then connect to it via the gateway. We just rolled out support for that [1] in the one we're making at mintmcp.com

[1] https://www.youtube.com/watch?v=8j9CA5pCr5c

Re: ChatGPT Developer Mode: Full MCP client access

#144

Post by moregrist »

WhitneyLand wrote: post #141
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

It’s not that simple. That would result in a brittle solution and/or cat and mouse game. The text that goes into a prompt is vast when you consider common web and document searches are. It’s going to be a long road to good security requiring multiple levels of defense and ongoing solutions.

If only we had a reliable way to detect that a poster was being sarcasm or facetious on the Internet.

Re: ChatGPT Developer Mode: Full MCP client access

#145

Post by jngiam1 »

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.

I do think there's more infra coming that will help with these challenges - for example, the MCP gateway we're building at MintMCP [1] gives you full control over the tool names/descriptions and informs you if those ever update.

We also recently rolled out STDIO server support, so instead of running it locally, you can run it in the gateway instead [2].

Still not perfect yet - tool outputs could be risky, and we're still working on ways to help defend there. But, one way to safeguard around that is to only enable trusted tools and have the AI Ops/DevEx teams do that in the gateway, rather than having end users decide what to use.

[1] https://mintmcp.com [2] https://www.youtube.com/watch?v=8j9CA5pCr5c

Re: ChatGPT Developer Mode: Full MCP client access

#146

Post by Huppie »

wrs wrote: post #122
horizion2025 wrote: post #117

Earlier quoted context omitted.

Isn't that just another guardrail that can be bypassed much the same as the guard rails are currently quite easily bypassed? It is not easy to detect a prompt. Note some of the recent prompt injection attack where the injection was a base64 encoded string hidden deep within an otherwise accurate logfile. The LLM, while seeing the Jira ticket with attached trace , as part of the analysis decided to decode the b64 and…

Yep. https://gandalf.lakera.ai/baseline

This is genius, thank you.

Re: ChatGPT Developer Mode: Full MCP client access

#148

Post by dgfitz »

WhitneyLand wrote: post #141
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

It’s not that simple. That would result in a brittle solution and/or cat and mouse game. The text that goes into a prompt is vast when you consider common web and document searches are. It’s going to be a long road to good security requiring multiple levels of defense and ongoing solutions.

I assumed beeflet was being sarcastic.

There’s no way it was a serious suggestion. Holy shit, am I wrong?

Re: ChatGPT Developer Mode: Full MCP client access

#149

Post by dgfitz »

withinboredom wrote: post #133
ch4s3 wrote: post #104

Earlier quoted context omitted.

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

Your question is a bit like asking how a word processor is better than a typewriter... they both produce typed text, but otherwise not comparable.

Interesting, have you used both? A typewriter types when the key is pressed, a word processor sends an interrupt though the keyboard into the interrupt device through a bus and from there its 57 different steps until it shows up on the screen.

They’re about as similar as oil and water.

Re: ChatGPT Developer Mode: Full MCP client access

#150

Post by ch4s3 »

withinboredom wrote: post #133
ch4s3 wrote: post #104

Earlier quoted context omitted.

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

Your question is a bit like asking how a word processor is better than a typewriter... they both produce typed text, but otherwise not comparable.

I'm looking at their blog[1] and yeah it looks like they're doing literally the exact same thing the other tools I named are doing but with a UI inspired by things like shader pipeline tools in game engines. It isn't clear how it's doing all of the things the grandparent is claiming.

[1]https://blog.comfy.org/p/nano-banana-via-comfyui-api-nodes

Post reply on HN