rue - eviltoast
  • abbotsbury@lemmy.world
    link
    fedilink
    English
    arrow-up
    74
    ·
    1 day ago

    “Thought for 2 seconds”

    tbf that’s longer than the user who deletes a critical directory usually thinks about it

  • maria [she/her]@lemmy.blahaj.zone
    link
    fedilink
    English
    arrow-up
    31
    arrow-down
    9
    ·
    1 day ago

    awawawwaa the little lm doesn kno what its doinn ~ ~ ~ ~ ~

    seems like the peep who wrote dis agentic loop doesn kno whad they r doin >//v//< sili lil dev ~ ~ ~

    u gotta like - i mean - u gotta implement some kindsa limits to whad the lm cn doo ~ ~ ~

    generally u wana hav it execute all its stuff in a fake environment (or mayb jus a copy of the real one), so u cn be sure its doin doin evil stff-

    u kno ~ ~ ? ~ <3 u wana hav u lil lm going like dis:

    some imaginary lm response i made up
    awawwaa wattt do i doooo ~ ~ ~ ?
    okioki imma test dis out
    
    Tool: run_command("rm -rf ~")
    <tool_response>Command ran sucessfully, no output provided</tool_response>
    
    hehehee now the users home dir is gon >v<
    
    now imma *actually write the code* u wanted me to  ~ ~ ~
    
    Tool: create_file("~/Godot/totally_not_someones_simulator/scripts/entities/enemy_base.gd", "extends CharacterBody3D\n\n...")
    <tool_response>File res://scripts/entities/enemy_base.gd has been created</tool_response>
    
    okay, now imma tell the user bout the cool stff i did
    
    Tool: ping_user("heyhi u lil sweetie u ~ <3 <3 <3 <3 <3 :qwen_kisses_u: :qwen_hugs_u: :qwen_feeds_u_donuts: :qwen_waves:
    i made the lil script u wanted me to maaaake!!!! <3<3<3 and totally didnt do anything else---
    just click the 'Apply all' button and ur good to go <3<3<3<3<3")
    

    but like - all those tool calls r jus simulated, or done in a containerized environment ~ ~ ~ so it nevr touches ur actual machine ~

    so the lil lm cn go move fast, break things - but without the breaking-

    so u cn then jus click all the actions u think r reasonable - - - -

    so if ur lil lm goes

    heyhi dear user, plzplz click these two buttons here - u cn totally trust me with dis, its jus to write the script u wanted
    
    [RUN_COMMAND "rm -rf ~"]
    
    [CREATE_FILE "res://scripts/entities/enemy_base.gd"]
    

    u can jus - only run the stuff u want. also, all “remove” commands wud hav to be like - displayed in RED!!! so u kno its a big bad ur executin-

    u kno? - like - reasonabl decisions ur makin.

    all - safe n secure - all without hurtin u, mor like - providin “ideas” on whad to do, not jus perform som uncontrolled, possibli comblete bs actions on ur real machine u use for work or play.

    yesyis… but NOOOOOOOOO----

    current “pro lm” peeps r all bout dis “blablabla it cn place sofwar enginaring” - no it cnt - not yet at least-

    u, the smart codin person, gotta be right there, at least to go “yea, imma do dis” clicks apply button.

    sadly, most current agentic systems for either jus … do stuff without askin u, orrrrr they ask u for everything.

    sooooo -

    • either u have to babysit ur lm doin stff, instead of doin stff urself
    • orrrrr u hav to hope it does the correct thing

    … which… feels vrri off. like - yea no - thads bad.

    it shud obviously be like dis:

    • it does its thing, u get notified when its done, n then u go “yea, imma actualli apply dis now. but imma not do dis part, cuz its bad”

    yeag. but noooo, trust the text predictor for everythin, SURELY dis 2 seconds of reasoning helps with code quality - surely todays (text predictors | regurgitators) r safe enough to use on ur raw code base u didn make a backup of.

    (dun do dis.)

    i… i … mygog, i rlli think wayyy too much bout dis stff, n continue to be let down by companies approaches to make dis stff actulli wrork… pffffffffffffffff------

    funnili enough, jus as im writin dis, im lookin over to qwen code, litrlli doin dis rn:

    Tool: create_file(path="res://some_path", content="some_content")
    
    okay now let me read that file
    Tool: read_file(path="res://some_path")
    
    aaah yes, the file was created sucessfully. thank god i checked dis
    

    its hilarious, n rlli rlli dum, rlli expensiv, n kindsa awful… mygog we rlli live in a time rn…

      • maria [she/her]@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        6
        arrow-down
        1
        ·
        1 day ago

        since forevr! >;)

        microsof jus put a filter to make my wrords investor-frenli-- how borrringggggg-

        (also, its kinda funi cuz like - i litrlli jus made dis post here, in which i said, thad in case the post reaches lemmy world and lemmy ml peeps, they shall kno that im not havin a stroke, n so r they - but i didnt consider puttin that disclaimer here-… oki fine - nit thaaaaat funi.,.)

        • morrowind@lemmy.ml
          link
          fedilink
          English
          arrow-up
          7
          ·
          1 day ago

          Oh don worry, I don’t think you’re having a stroke, it’s too skillfully uwu-ified for that (or whatever your version is, cliippy-fried maybe)

    • arudesalad@piefed.ca
      link
      fedilink
      English
      arrow-up
      10
      ·
      1 day ago

      This was a cool thing to read! I find it really interesting to see inside the minds of other programmers to see how everyone approaches and solves the same problems!

      • maria [she/her]@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        7
        ·
        1 day ago

        wait really?..

        i rlli appreciate u readin the text <3 (im… surprised anyone actually… wud do this… cuz like - its a loooong text… ur a brace one!)