I was curious how well gpt-4 could de-noise the text. With the prompt:
uncover the text from the message which as had noise introduced:
In Gramm@r, an @R+icle_Is.anY memBer I6.@ claSS oF_dedicateb_WOnbs that arE used m|th_No0n phR@ses tO MarK_Th4 id4ntifiabilitY of +Je ne64Rents of THe noun qhnases. Th4 c@tegoRy of articles constitutES a panT oF sPEecJ:
It was able to perfectly recover the original text.
That's pretty incredible! I did the same with a paragraph from another article I was starting to read on HN. (here: https://news.ycombinator.com/item?id=39740654) I put it into this and cranked the slidey thing all the way up then gave this to GPT4:
uncover the text from the message which as had noise introduced: whEn_O_mIYeD uq2taTe.@t_tJ4 9`oght.of +Je pandeM|c?_I fInA1ly.reCykl4d @ dAMker?S_BOX OF useR.90|dEs fIr_tJ|n9s.I_No_lIr9er_OwNEd: a toaSt4R:Iven, A_Palw_+iLI+,_a.vxB. th@t_B0C_hab moz3b wit9_Me_From CHEls4U:+o_We2+_+hI1ly_To PaRk_51Op4, ther:Ir to~6rAmerCy_ANd Crown heoGhtS and pet48:XooPEn VIll4Ge, evEN thoUGh_o jUdN?+_4bd4d or r4tnIeVEb @nythirH:from +JE~CollEction.in yeanS _7HE_OlDEs+.MUr0als w4rE_FrIM tJA.mid=90s, wher I LA6T_M?.pAnenPZ^.JImE aNb 2tarTed.B@IldIng a M4naGerie_O6 applianC42.aNd.9aDgEt2 FoR.mJich_o.mas so1ely rEsponsIB1e: Instr0Ct|Ins Wer3M?T online.PJEN,_So.it:M@2.T9nO09H.+hesE CheAPly qRinteb book1Ets tHat O_unberstoID Th4.op4r@P|nG_lOg|cs.i6.m?.devicES _Sowe 9uIdeS_HaD.2ectIOns.Ir.ClEAnINg, mainTENAnce, troub1esHOotINg" arD req@i8?.Oth4R2.JUd diaGRam2 +J@+ mIU1d_HelP m3 In6A8.jiM.TI.f|$_4MvTHINg +J@+.drOk4._3zEry mAMUA1 dEPOsiT47.|r tJ@+.dI$_Was A_sign I6.my INT4r+|ir.+o_c@r4.F0n~TJe_TJiNG@maJIG_it came with
and while the resulting text wasn't perfect, it did get 90% of it and it stayed true to form.
"When I moved upstairs at the height of the pandemic, I finally recycled a banker's box of user guides for things I no longer owned: a toaster oven, a Palm Pilot, a VCR. That box had moved with me from Chelsea to West Philly to Park Slope, then to Gramercy and Crown Heights, and even though I hadn't added or retrieved anything from the collection in years, the oldest manuals were from the mid-90s, when I last moved. I started building a menagerie of appliances and gadgets for which I was solely responsible. Instructions weren't online then, so it was through these cheaply printed booklets that I understood the operating logics of my devices. Some guides had sections on cleaning, maintenance, troubleshooting, and repairs. Others just diagrams that could help me navigate fixing anything that broke. Every manual deposited in that discard was a sign of my interaction with caring for these thingamajigs it came with."
I'm kind of shocked honestly. I can make out some of it but a lot of it is too jarbled but it's interesting that it manages to pull the text back out, even thingamajigs!
uncover the text from the message which as had noise introduced: In Gramm@r, an @R+icle_Is.anY memBer I6.@ claSS oF_dedicateb_WOnbs that arE used m|th_No0n phR@ses tO MarK_Th4 id4ntifiabilitY of +Je ne64Rents of THe noun qhnases. Th4 c@tegoRy of articles constitutES a panT oF sPEecJ:
It was able to perfectly recover the original text.