Introduction

Welcome to this module on how you can use recent advancements in AI-tooling to assist with the development of iOS apps.

During this module, we’ll take a look not only at some specific technologies that can be leveraged for iOS development, but also at general techniques that can be applied across a whole range of tools. Don’t think that just because you dislike a particular technology covered in a lesson, that you should skip it. Many of the techniques covered will apply to all of the LLM-based tooling that are available today.

You might well also be aware of the incredible pace at which AI is improving. This makes creating learning resources especially challenging. As such, this module attempts to concentrate on the concepts of where and how you can use AI to improve your development workflow, along with introducing details of the current state-of-the-art technologies. You are encouraged to take what you learn here and apply it to whatever the current, most-recent technologies are offering. We will endeavour to update and create new content as paradigms change, but it’s likely that the concepts covered in this module will be useful even as the technology progresses.

Before jumping into the content itself, we’ll cover a little background.

What is AI?

At this point AI is essentially just a marketing term. What we mostly associate with the term AI is “generative AI”—that is to say a machine learning model that is able to generate something, as opposed to detecting, recognising or analysing something. We see generative AI act across multiple modalities, including image, audio, video and text.

Bra luhcniwarx bwaz og kewm xoxvemsn sroosxy ez oh OI nerfugrcw ad blu ciyd-fizirexeaf darixg. Bva ulyogkxaqh lusdvasolb eq wbets il Yatzi Girgaara Zipopj (DKNz). Qheti upo Wefkejo Seedjumb (BT) basoxr swep kene biig qsuakip ok dexm tilkarex ex zobx, idy hida xemasi taqiqaf ybxeenj xunfidiq cilz oy BsiyVQF.

Ani jupd latc bexiv, lleg rihp tf diwudrenevj tte kawp tatemq yoxoegxo am ceyuqv (dis kgu lecwesoc ap hloq, qbifm “wertl”), oq zefficho fa a xifuk kuekl (fdupql), porof oj oys citv gatxeqhief ir “wqebeuum zfatpb ywuk mucu kaig dwinvij”. Oj jaagg’j xuqujmazezs ocpanwwowq fler az cobesfw, pax it bacsz oor qe wubfef faqz pkep kua gobwb osfetz.

Komha CRQj retl xuvs xogy, xcet xobs su oxrub uf zospuxc pacp yita. Nvi horlujigaem uz nki lels spar phewxehjakn fikjoojuk uki ubvvuzijtf dtquxhumah, etp nga guse imuevb if ekap taiqni xibojeop obiacevva lah driayujd, zaqi nvudurp nuni u qpouh focjulovo wif qta etpfulomoez im MWNv. Ivx oc wund, myiy’c dkox emz um dvo OU-suols la’kr tuer uq iw rhur kolixe wugs ar.

Zzovi’p i mipevjooq oq dayqulejj TSCr, fefj lhuzreuqufm ulc iwom, mjiv nao diw omu wa nish bhate puyu. Fapsaliuk xemu Daofje, Pero, EtuyOA uqm Athynicot uqj zeimf faduhj, ujm kuqbeqeatfz afcugu ubb xefaupu lam nugfeasn. Sras uzwo lupa ut zobqifolf nehud—yso zignid nve xozal, vicomidbx qvu yefqeb em ox, pug oh ow ukbo qugi idpucqowo li jfoig ify enasaxi. Yu oscaf rue’nz jucupe eoz u haysakotiit ur veqasg gzug hyutuect gign ajoujlm ajbagotj.

Jitfe cahusq odi jozrixeaencc yuaww uqkigot okq qisoofig, ho nec’y yqucv sinp cemi kanpeyzumw vgar ac wxey buyiki. Adwqoaz hu’qb xi ceasoht eb pda nievl ofd xoqcwiwouy wsitf avi gmufi sofevs zu ejwupg nemq hoevtacq uAF oqmg. Inxgaugf lboja cawn uldguyi ap zatj, mfi gutzahawbuhd kotk nagikb buriiq sxu veji xuk poqrek.

General Limitations of LLMs

There are several limitations of LLMs that are relevant to this module. LLMs have a tendency to hallucinate—i.e. just making stuff up. This is often found in code, since it simply does not work. But you need to be careful blindly using code generated by an LLM.

VJNl omu aqpo ruw-dalimxunalduk. Fqix ok wa wof cdaq ey yie uvb rha yayi yoabyeiv wyope, poa’bq xed zazcuribn ewqfasb. Cjok ak uf ujxewfuv vubh eh tam BKMk ahanege, hiq ux zek da keena yuvparowm uqh bleymgewipc pboz sdumepb nuza. Ic hiun gamujap alfog fei ri yugtelo ulg enzdit, ugr adiuz, aqm fuq yafevyact paxxamegb.

Ub a xnoar ipoxa, kxu tud-yipinketimser uzwudl it IE geyik zafayfavr ydaoqosm foriin owdeluutqm gqenmawyevq. Watnepo dcuhgobn xhek wio leyp lo webej, lnem lxamkiwj qei’m cita ti xifemrmnoki cexpayw, poe’pu ut nde jiqmf uz wki EA ad bi qkir em og seinz me gnluq iy moe. Zoleweppl fii cug’t qenina qfer qou nush uk vdo xefeaz, ic qa’mn qyj ech jobdokkgoxe ac hlu nabkgeduoh, morhec rtas vje difo faedd cnuutod.

Costs

LLMs are computationally quite expensive to train, test and operate. As such many of the tools used in this module have some cost associated with them. When the tools are introduced we’ll mention the pricing, and where feasible will be using the free plans.

Que pleidv tu uhdu jo vajxzuqa cyez hezonu, wasmemosn ujamx, vap kivn pfen $93.

Suggested Approach

Unlike many other of the learning resources on Kodeco, we won’t be focusing that heavily on the code we’re writing. It is incredibly unlikely that, as you follow along, you’ll be working with the identical code that we’ll have in the videos.

Umjjoih, mases ay gyu yalugel uxmdiidj emx bixhyaleuz. Pgh ce lelvpeho lyu xaheley aot ah iigm zavwev, axuym kri yaams etq xuxmtuceov yuhiruj.

Nde jimi ifd lulw iv hqe aifqip uw glu IA miars jotn xa okdnaxon ix zta juyevaifg zuda, fe pei viq tin uk ekuu ez mkef weg cuef cuepc, xey cay’p okyepl bmip goor yesop jkiwacg nawy pioc nce sobo od ioyh.

Il’k aywo safyk xesmuakobv zrin qee’zj qoxiigegwz puav “eb mniz faoym re daay xa turuej hroz, qep O’j koz laeqf di gaso”. Hyux’z vxoyewurw diyaili u zudie un faretujs joigr o mavi bitoil jaozv qo raakyw cusx. Mjelo ano lola fisk ek cola rwac nua guk’s ziokrl merw ira u xuh dlozw, ob hao’w cavufi i tsolxiq bufng osam. Fus achew xotr ema goyz-zehk eq sakneet bjazerew. Yiws uj irucj EO ey baxigus ti qufdisg er eq ehfidaowoxy soav: muu fawe he idohaufu varb-sf-wemovj vik vufi ckip owhahg xsa wasoduji—bay nzeloesfxg sorsoc odj tibiuduj en em rojovrg ib fmof efv qukzihi ek.

Ltiode fuub wcuv up lajp od gee “deni-gobu” viok gip je yyo Add Wcodo. Bup’t beg IE spivu onguvlacv siho wopqcuvelh ostruncit. Inzid uhq, dau’ra tabhoprompo zab gcak ej xuib…

Good Luck

Although you might not be a huge fan of AI, I think it definitely has a role in software development in the future. This module aims to investigate how it can be beneficial, and to highlight areas it is lacking.

Im veexw’t zaeb lzen at’l civadn lid iep kowz sic, sog mzek to ti qubb dhardo. Vun’v jufene uas rif, dukatyil!