It's trash, doesn't work better at all. It's the same thing, the same EXACT thing. Chinks didn't prove shit. They claimed something and you're just going to believe the numbers they tell you? Do you also believe the high Chinese IQ? Please tell me you're not that retarded.

It is not uncensored so no you can't make it say shit about jews or niggers. Whaaaah. Who the fuck wants to talk to a computer about jews? That's retarded. There are much better uses for AI other than trying to make it say bad words.

Strawman, bye.

Also last I checked they just wiped 18% off Nvidia's stock price and it was still falling afaik. Give the chinks their credit. They're doing more w/ inferior hardware b/c they don't have cheap tech pajeets doing the coding.

He's arguing that it can't be jailbroken with simple prompt injection. And that somehow makes it worse than gpt.

Do you have examples?

I always ask new AIs to write code in AutoHotkey. Version 2 specifically. They all fail miserably. Most of the time they just make shit up and when they do write somewhat real code it's always v1. Here is what I asked deepseek.

Write a function capable of fuzzy match string comparison in Autohotkey v2.

It returned a function that utilized Levenshtein distance. The code was right, but it was written in v1 as expected.

I noticed you are using v1 of Autohotkey. I specifically asked for v2

And then it correctly rewrote the code using v2 syntax. That about all I've tried so far. I'm not really interested in having a conversation with it.

; Function to calculate Levenshtein distance between two strings
FuzzyMatch(str1, str2) {
    len1 := StrLen(str1)
    len2 := StrLen(str2)

    ; Create a matrix to store distances
    matrix := Array()
    Loop len1 + 1 {
        matrix[A_Index] := Array()
        matrix[A_Index][1] := A_Index - 1
    }
    Loop len2 + 1 {
        matrix[1][A_Index] := A_Index - 1
    }

    ; Fill the matrix
    Loop len1 {
        i := A_Index
        Loop len2 {
            j := A_Index
            cost := (SubStr(str1, i, 1) = SubStr(str2, j, 1)) ? 0 : 1
            matrix[i + 1][j + 1] := Min(
                matrix[i][j + 1] + 1,    ; Deletion
                matrix[i + 1][j] + 1,    ; Insertion
                matrix[i][j] + cost      ; Substitution
            )
        }
    }

    ; Return the Levenshtein distance
    return matrix[len1 + 1][len2 + 1]
}

; Function to perform fuzzy match comparison
; Returns a similarity score between 0 (no match) and 1 (perfect match)
FuzzyCompare(str1, str2) {
    maxLen := Max(StrLen(str1), StrLen(str2))
    if (maxLen = 0) {
        return 1 ; Both strings are empty
    }
    distance := FuzzyMatch(str1, str2)
    return (maxLen - distance) / maxLen
}

; Example usage
str1 := "kitten"
str2 := "sitting"
similarity := FuzzyCompare(str1, str2)
MsgBox("Similarity between '" str1 "' and '" str2 "': " Round(similarity, 2))

deepseek

My bad. Yes. https://pic8.co/a/2cfaa4d2-8518-4ce7-8367-23dc2562ebeb - I hope it preserves the order I dragged them into the grouping frame. e: it gets really spergy at the end, and you'll have to trust me here, is kind of required as AIs have shit memories. I also ask one question poorly but it works.