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

MCP server for Ghidra

github.com

Post reply on HN
Print view View original

51–60 of 77 posts

Re: MCP server for Ghidra

#51

Post by otabdeveloper4 »

dragonwriter wrote: post #45
otabdeveloper4 wrote: post #44

Earlier quoted context omitted.

LLMs process information in a strictly sequential manner. It's their core capability and what makes them feel so anthropomorphic.

> LLMs process information in a strictly sequential manner. "LLMs" as a class do not. Most LLMs, because most LLMs are autoregressive models, but diffusion LLMs exist and are not sequential in the way that autoregressive models are. > It's their core capability Being sequential is not a capability at all, much less a core one defining Large Language Models. > and what makes them feel so anthropomorphic. I disagree wi…

The gimmick of the LLM is that it outputs text sequentially, as if it is talking to us. That's what makes them feel "alive" and "intelligent" to us. (And yes, ironically it's this sequential nature that actually limits their intelligence in practice, but whatever. The AI hype is about appearances, not facts.)

Re: MCP server for Ghidra

#52

Post by jevyjevjevs »

qwertox wrote: post #10

Which tools can currently invoke MCP? I have read only a little about MCP and got to know that Claude's desktop application is capable of using MCP locally. Are there any chat interfaces which allow using MCP remotely? I would like to be able to specify MCP endpoints and the functions they offer in ChatGPT's, Claude's and Gemini's web interfaces so that I can have them call my servers remotely. A bit like "GPTs" and…

I'm using Librechat which I've found to be quite feature complete. I updated an Obsidian MCP to get my most recent journal entries to act like a therapist. Example setup here: https://www.jevy.org/articles/obsidian-mcps-to-work-with-not...

Re: MCP server for Ghidra

#54

Post by rowanG077 »

otabdeveloper4 wrote: post #51
dragonwriter wrote: post #45

Earlier quoted context omitted.

> LLMs process information in a strictly sequential manner. "LLMs" as a class do not. Most LLMs, because most LLMs are autoregressive models, but diffusion LLMs exist and are not sequential in the way that autoregressive models are. > It's their core capability Being sequential is not a capability at all, much less a core one defining Large Language Models. > and what makes them feel so anthropomorphic. I disagree wi…

The gimmick of the LLM is that it outputs text sequentially, as if it is talking to us. That's what makes them feel "alive" and "intelligent" to us. (And yes, ironically it's this sequential nature that actually limits their intelligence in practice, but whatever. The AI hype is about appearances, not facts.)

Are you saying that if visually LLMs would not output text sequentially but at once they would not be as successful as they are?

Re: MCP server for Ghidra

#55

Post by dockerd »

jevyjevjevs wrote: post #52
qwertox wrote: post #10

Which tools can currently invoke MCP? I have read only a little about MCP and got to know that Claude's desktop application is capable of using MCP locally. Are there any chat interfaces which allow using MCP remotely? I would like to be able to specify MCP endpoints and the functions they offer in ChatGPT's, Claude's and Gemini's web interfaces so that I can have them call my servers remotely. A bit like "GPTs" and…

I'm using Librechat which I've found to be quite feature complete. I updated an Obsidian MCP to get my most recent journal entries to act like a therapist. Example setup here: https://www.jevy.org/articles/obsidian-mcps-to-work-with-not...

@jevyjevjevs,

Can you add rss feed to your site blog? I found few of the articles interesting and helpful. I would like to subscribe but I don't see rss or email subscription.

Re: MCP server for Ghidra

#56

Post by dataangel »

brokensegue wrote: post #32
vessenes wrote: post #19

Earlier quoted context omitted.

Hmm, specifically when it comes to reverse engineering, you have the best benchmark ever - you can check the original code, no?

that requires LLM as judge

no it doesn't, you just diff against the real source code. probably something more fuzzy/continuous than actual diff, but still

Re: MCP server for Ghidra

#58

Post by gnfargbl »

Xx_crazy420_xX wrote: post #42

For LLMs to solve code I think they should be AST-native. Code is a tree, not a sequence — yet we feed it to models linearly, with no explicit structure. Todays models lack recurrence or true memory, so they can’t reason over hierarchical structures effectively.

Has there been much work on reversing binaries into an AST form? It seems like something that somebody would have thought of researching, but I've not come across any efforts.

Is it something you can do generically, or do you need to know the specific compiler? Do you need to know the specific language, even, or could you perhaps create some other hypothetical AST in a different language that would have led to the same binary?

Re: MCP server for Ghidra

#59

Post by brokensegue »

dataangel wrote: post #56
brokensegue wrote: post #32

Earlier quoted context omitted.

that requires LLM as judge

no it doesn't, you just diff against the real source code. probably something more fuzzy/continuous than actual diff, but still

Proving that two pieces of code are equivalent sounds very hard (incomputable)

Re: MCP server for Ghidra

#60

Post by randomtoast »

I hope that one day we have a tool that can convert any proprietary binary to source code with a single click. It would be so much fun to have an "open source" version of all games. Currently, there are projects like https://github.com/Try/OpenGothic and https://github.com/SFTtech/openage, but these require years of community effort.
Post reply on HN