[DredgenSun]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

[Xrptcb]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

thats what I am trying to do, really write good rules for, is the parsing piece I noticed DeepSeek has less guard rails in place and you can manipulate the results a little better.

[DredgenSun]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

thats what I am trying to do, really write good rules for, is the parsing piece I noticed DeepSeek has less guard rails in place and you can manipulate the results a little better.

If you get LLM studio, you can run DeepSeek offline with no moral constraints, try that!

[Xrptcb]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

thats what I am trying to do, really write good rules for, is the parsing piece I noticed DeepSeek has less guard rails in place and you can manipulate the results a little better.

If you get LLM studio, you can run DeepSeek offline with no moral constraints, try that!

I ll give that a go

[NaN485]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

thats what I am trying to do, really write good rules for, is the parsing piece I noticed DeepSeek has less guard rails in place and you can manipulate the results a little better.

If you get LLM studio, you can run DeepSeek offline with no moral constraints, try that!

Great recommendation. ty for sharing!

[DredgenSun]

When it comes to parsing your content, data and experience, AI, specifically LLM's are 2nd to none for being an assistant

thats what I am trying to do, really write good rules for, is the parsing piece I noticed DeepSeek has less guard rails in place and you can manipulate the results a little better.

If you get LLM studio, you can run DeepSeek offline with no moral constraints, try that!

Great recommendation. ty for sharing!

You're welcome bud

[MarjuTajum]

they said "PentestGPT is able to solve easy to medium HackTheBox machines, and other CTF challenges." means now CTF challenges will be AI battles?

[monalisa]

https://github.com/GreyDGL/PentestGPT works great for me.

I will definitely give that a go. building out the lab this weekend

---

I say dont bother. by design, LLMs can only create mediocre code, because mediocre code is most likely to occur in the dataset. pentesting and bug finding are not at all mediocre tasks, I am pretty sure that LLMs are going to struggle no matter how good they are compared to GPT.
there are specialized AI models for binary analysis and such, but I only hear of them through articles, no published models

yea same, I was trying out deifferent stuff, maybe automate some Google dorks with AI and kinda go from there. I was just curious if anyone had success with a tried and true method

---

try out ollama and the uncensored models. not as good quality as deepseek so far, but not as much limits also

that was really the primary inhibitor some of the standard LLMs set limits on searches

If you wanna automate google dorks, just use the exploit-db... thousands of confirmed working dorks in there.

[Jenc1]

You can find pentesting gpts at openai, cant you? Or are those worthless at all?

[Xrptcb]

You can find pentesting gpts at openai, cant you? Or are those worthless at all?

With those they are kind of hit and miss, based on how the phrasing is set because of the "morality restrictions"

---

https://github.com/GreyDGL/PentestGPT works great for me.

I will definitely give that a go. building out the lab this weekend

---

I say dont bother. by design, LLMs can only create mediocre code, because mediocre code is most likely to occur in the dataset. pentesting and bug finding are not at all mediocre tasks, I am pretty sure that LLMs are going to struggle no matter how good they are compared to GPT.
there are specialized AI models for binary analysis and such, but I only hear of them through articles, no published models

yea same, I was trying out deifferent stuff, maybe automate some Google dorks with AI and kinda go from there. I was just curious if anyone had success with a tried and true method

---

try out ollama and the uncensored models. not as good quality as deepseek so far, but not as much limits also

that was really the primary inhibitor some of the standard LLMs set limits on searches

If you wanna automate google dorks, just use the exploit-db... thousands of confirmed working dorks in there.

I am going to check those out