Pratica di Shadowing: I Spent 1.5 Billion AI Tokens on Absolute Slop - Impara a parlare inglese con i video

Scegli una modalità di pratica

Ogni modalità apre una sala di pratica a schermo intero.

251 frasi

Se le frasi sono troppo corte o troppo lunghe, clicca su Edit per modificarle.

I spent 1.5 billion tokens on this project and put it through GPT-56-SOL on high.

I did have it spawn extra workers on high to try and knock this out in a couple days.

Overall, about 24 hours of consistent compute runs.

There were some times where it stopped because of usage errors or a reset needed to happen.

But I did use, I think, four resets of the $100 plan and just a ton.

I got lucky in opening.

I had a reset as well.

So I was able to use a ton of inference.

I don't know what that 1.5 billion tokens will equate to in dollars, but I would assume probably around $10,000, maybe more.

And I wanted to say this was terrible.

It made slop.

and I wanted to kind of showcase it because what I had was a .NET project.

Most people know my Windows utility that's written in PowerShell

and my .NET basis I've built over the last year or two off and on just kind of hacking away at it.

It had roughly, I think 5,000 lines of code and I wanted to expand it out so it has feature parity.

An idea behind Win OneShot was just to have something kind of on deck in case something happened with PowerShell, I could easily translate everything to .NET.

So all the functions I built was like changing registry edits.

Instead of doing a set item property, I could actually just force that through the .NET libraries instead of using that section of the code.

So I could always fix windows essentially.

So it's always been kind of like my fail safe or a possibility of maybe doing a standalone.

But I wanted to see what AI could do with it.

So I already had the scaffolding.

I already had the structure.

I just needed to feed it a roadmap, a spec sheet, and then have it build out of tasks for it to run.

And I thought, hey, let's split this up with workers.

And I got this whole idea because I saw something online about Bun being rewritten and ported from Zig to Rust.

And I was like, well, shit, if it can do that, surely 5.6 Sol High could do this.

This is nothing compared to that kind of port.

And sure, they use Fable 5, but I was like, well, 5, 6 old should be good enough.

And I want to say, I think we're to the spot where it's not really about the models.

It's about you, your ideas, your skill, your software development ability.

And I think this is always going to be a thing

that you just I don't see a way around this where you have to think through the problems, the structure, and AI just can't think for you.

You can tell it and direct it, but my directions was have feature parity.

Here's my parity project with PowerShell script.

Here's the scaffolding where it already has the functions in place.

Just add the missing functionality, whether that was, I think win 11 creator where it creates an ISO or,

uh, the app X removal that was just added in this last update to when you till.

And I was like, I, that should be relatively easy to do maybe five, 10,000 lines of code.

And at the end of the day, we ended up with 169,310 lines of code that was added.

Holy shnikes, Batman.

That is an absolute ton of code.

What does that mean when you have, well, we'll just call it 170,000 lines of code that was changed.

It means the project's no longer years.

You don't know what's up.

You don't know what's down.

When you look at the code base, it is no longer maintainable.

You just have so much stuff, you're better off just starting from scratch again.

In this instance, I'm going to show you what it created, and then I'm going to show you what it had to work off of,

because they're just two vastly different things here.

What it created was this.

Pretty good project on launch.

I did notice right away on launch, it launched considerably slower.

Well, to be expected with over six figures of lines added to the project.

But with a built binary, it's going to be menial to the end user.

Compute these days is so cheap.

And most people, you know, most software developers, even before this, had bloated projects, and it really didn't affect performance that much.

So I looked at it, I was like, yeah, all right, that's good.

Now, when it first spit out, it was all one single column.

So of course, a couple of reiterations needed to be made.

It was like, all right, let me give this an honest try.

Let's split it up.

Let's match this.

Did okay job after all of that.

We still have like a category load fail element not found down here.

Trying to track that down.

I was like, okay, that needs to be reworked a bit, but it does work.

And then for the tweaks page, I was like, okay, Let's see what happens there.

It tries to inspect all the tweaks and then tell you what the current state is.

Sometimes it can do this.

Sometimes it can't.

It just depends on the tweak.

But to try and go through and maintain this, let's say I was to release this on the world.

Well, people are going to go, hey, the acrylic blur is applied, but it says not applied.

And you're like, well, I, okay.

And then there'd just be tons of issues like

that with this iteration and you're relying on an LLM prompt to fix this.

At this point, the code is pretty much unreadable, unmaintainable, and that's a problem, especially if you're charging money for something like this.

And this is where I think a lot of people are gonna get in trouble.

So this is what happened with the tweaks, configuration.

I had to kind of move this around.

Initially, it made this check boxes.

Then I was like, no, those need to be buttons.

That was fixed the updates just didn't work at all i

think they still don't work something about state infection i was like okay well i'll go ahead

and click this hopefully it doesn't blow up my system it kind of works on a lot of things

but it's close but not and i think the fallacy here for someone

that never done programming before i even saw i think it

was a meme online where someone was like the new state of development, you know, idea, first build,

and then the last 10% is this massive chart where the last 10% took up more than 60, 70% of the time.

And honestly, this is kind of how it's always been to try and polish that last 10%.

The problem is, when you have so much tech debt from all this AI and iteration for big projects, it's impossible to read the code.

So that last 10%, if AI can't fix it, you're kind of screwed.

It just doesn't, you're basically relying on it 100% with no safety net.

So you can't go to market with something like this.

It's just really important that people have that or know that up front.

And you might be thinking, Titus, just use a different model.

Models will not save you from just plain bad foundation.

You have to have maintainable code.

100

It has to be readable.

101

And then you could pass it off.

102

I've also heard horror stories of like CEOs

103

or someone from the C-suite making something or vibing something up and then handing it off to a development staff.

104

That is the opposite of how that should go.

105

It should be the development staff makes a mock and then gives it to the C-suite to look at, not the other way around.

106

Where we're failing with AI is, or LLMs, whatever the hell you want to call it,

107

is normal people still can't make software let's just be real here let's i'm going to say

108

that and scream

109

that from the mountaintops you have to know the foundations you have to think through the projects

110

and understand what you're getting into even when i gave it proper instruction

111

and just let it run wild it completely screwed everything up now it's on git

112

so it's not a big deal let's get to and rewind to show you what I gave it, where we were at using Git.

113

And if you don't understand Git, you should not be doing any of this.

114

Git is the very first thing And it's so important to understand.

115

I can't say that enough.

116

It will save your bacon so much because this is 170 lines, 170,000 lines, thousands of dollars.

117

Let's say if it's a company, it would have been probably tens of thousands of dollars it would have spent on.

118

And now it has to be thrown away.

119

So I'm going to go directly to this private repo because I didn't want this to be public.

120

If you're interested in the code, I could make it public so someone can look over it.

121

But I'm going to go back to before this all started.

122

So here's the commit history for win one shot.

123

I'm going to just grab this because I haven't pushed any of these changes.

124

And we can just discard pretty much all of it.

125

So the commands get reset, dash dash hard, and this.

126

It's going to reset everything from here.

127

So once we do this, say goodbye to the project.

128

And then you're going to see how the project changes.

129

Look at the current structure.

130

And here we go with the git reset.

131

So now we're back to this.

132

And if we look at what we have, we have a sources, test tools, all this.

133

These are untracked.

134

We could actually get rid of these.

135

We're going to just do a git clean FD.

136

It's going to push out all these tests, everything that was wired up from it.

137

So now we're working off of a clean from May.

138

I'm going to do a clean and then the build really fast.

139

It looks like there was a bunch of artifacts left over.

140

So essentially we can use LLMs.

141

I'm not saying I'm not anti-LLM.

142

We can use it to troubleshoot this.

143

Like, why didn't this reset happen?

144

And it said there's a bunch of leftover sources in the OBJ directory.

145

And then we looked through, it was still looking and referencing some of those sources from the source directory that was created by the LLM,

146

which was causing the errors.

147

So now that that's done, it probably will wipe out that.

148

We're going to clean those generated paths and restore and build.

149

And now we should be able to build the full release.

150

Now it's successful.

151

Now we can do a .NET run.

152

And here is the project as it was before the LLM took over.

153

Obviously quite a bit simpler, obviously not so much bloat.

154

I did kind of like the sidebar.

155

So while this seems like a massive waste, it did give me some ideas.

156

Like I really did like that sidebar pop out.

157

I might actually take that, implement it.

158

That's actually a pretty good thing.

159

Obviously still have to work on the config page.

160

Updates page, I was kind of thinking through a few ideas here for like default security and disabling.

161

This all kind of has a few different changes here.

162

Obviously it's not reading my Windows version.

163

This is actually Windows 11, not Windows 10.

164

So this is not without its own bugs, because it was hand coded by me.

165

But you got to look at the code at the end of the day, like this is what was there.

166

It's so much easier to just kind of right there's my views.

167

I don't have five or six different sub projects.

168

It's very maintainable in this structure.

169

So I look at the spec sheet and all the stuff that the LLM built over that.

170

And the problem isn't the models.

171

The problem is me, my ideas, how I instructed it, and then just letting it run wild without proper checkpoints.

172

Bigger projects need those checkpoints.

173

You need to understand before it just completely goes off the reservation

174

and then makes 150,000 lines of code when it should be 10,000 lines of code.

175

Well, I don't even know how many lines of code is in this entire project.

176

Let's find out.

177

Here we go.

178

Roughly about 10,000 lines of code.

179

So you see the difference there.

180

And to manipulate this to be better,

181

like removing the checkboxes, making those icons and those cards like I did in WinUtil, you can do all of that here.

182

And the lines of codes change for that kind of implementation.

183

We're talking maybe 100, 200 lines of code.

184

Maybe it's in that ballpark.

185

And it's so important to understand you can't just let these things run wild.

186

So what this should be is go from here and say, hey, let's improve the cards.

187

Instead of check boxes, let's add cards with icons.

188

And then slowly go through and change the things that you need changed.

189

And then go from there.

190

That's probably the biggest takeaway from this is I think we're in an era where you have these extremes.

191

You have people that don't have any business making software, trying to vibe up something and then handing it off to a professional.

192

That should never happen.

193

Professionals need to make it using these tools that can make it faster, but they are the ones to commit that structure,

194

do those checkpoints, make sure it's doing it properly and making sure it's maintainable in the future. So important.

195

And then the second thing is There's also people, the tech bros out there that just say, hey, make me an app, go.

196

And then just sit there and reiterate, spending billions upon billions of tokens to make something that kind of works.

197

But as soon as they go to market with this, it's going to fall apart.

198

And then it's not going to be maintainable.

199

And then all of a sudden they sold something that just doesn't work at all.

200

And they're just like, oh crap, that was false advertising.

201

And it just runs down this entire terrible cycle.

202

So out of my last video, 10 projects for AI to do that I've done, I wanted to make a video today saying,

203

here's where AI failed miserably.

204

And I don't blame AI for this.

205

I blame me for it.

206

I should have checked in.

207

It should have been a phased approach where after each phase, I'm checking the code and going, nope, stop, stop.

208

That's just bad.

209

No, we don't need to do that.

210

We don't need to write 20,000 lines of pester tests for something that should never even be tested.

211

We don't need to do all these other things

212

that it ended up doing because it was just not the right way of doing it.

213

So it ended up implementing it incorrectly.

214

Not that it didn't work, but it's not done how I would want it being done.

215

So hopefully this all makes sense to somebody.

216

Don't one feel like, hey, you're a normal person and then you're just gonna be able to develop software that you never developed before.

217

Small software, sure.

218

Dashboards, go for it.

219

I think normal folks should do that all day long.

220

I do it.

221

It's great.

222

Like just look back.

223

Websites, wow.

224

Fantastic at websites.

225

But when it comes to big projects, I very much caution you.

226

You need to think of it as a pair programmer code review.

227

It's fantastic at those things, fixing really like nuanced bugs.

228

Like why the hell is it doing this weird glitch right here?

229

Tell me why.

230

And then it'll spit out and go, well, you idiot, you're utilizing it this way improperly.

231

And you should be pulling this library.

232

And you'd be like, Oh yeah, that, that makes sense.

233

That's where it's at with great, like big projects.

234

It's fantastic.

235

It's a great tool for it, but it will never replace the programmer.

236

It will never replace the developer.

237

I think it'll cut down or make that developer a lot faster

238

and it'll make them be able to do a lot more with less, but a replacement is not.

239

And that's what this video was.

240

This is just kind of a state of 5.6 Soul.

241

You could say, hey, Fable 5 would have done a better job.

242

Maybe, probably.

243

I mean, I couldn't imagine doing a worse job than this.

244

But I don't think it's a model issue.

245

I think it's a me issue, an ideas issue, a foundation issue, an instruction issue.

246

You have to think through these projects.

247

You have to think through these problems before it encounters them.

248

So it sets it up with a structure that can be maintainable and usable and verifiable.

249

It's so important.

250

anyways I hope this helps somebody with

251

that let me know your thoughts down in the comment section and I'll see you in the next one

Scarica l'app

Tutto ciò che serve per parlare fluentemente

Pronuncia con IAVoto per ogni frase

Pratica IPAPadroneggia ogni suono

VocabolarioCostruisci il tuo lessico

Gioco di vocabolarioImpara giocando

Scansiona QR

Download on theApp Store Get it onGoogle Play

Stesso Canale

I Rebuilt My Entire Website in Astro… Was It Worth It?

Daily ConversationWorking Adults

Is AI Doom Real... or Just Good Marketing?

Business EnglishUniversity StudentsWorking Adults

FOR YOU

Video consigliato

212 frasi

Sam Altman x Nikhil Kamath: How to Win When AI Changes Everything | People by WTF | Episode 13

Business EnglishUniversity StudentsWorking Adults

Vocabolario e note di pronuncia per questa lezione

Questo video contiene 251 frasi e 2877 parole da ripetere con lo shadowing. Il parlato dura 16:48. Chi parla ha un ritmo naturale di circa 171 parole al minuto, vicino a una conversazione quotidiana. Il 86% delle parole rientra nelle 3.000 più comuni dell’inglese; conviene studiare le altre prima di iniziare.

Vocaboli chiave di questo video

15 parole del video che vale la pena imparare, con pronuncia e significato:

Parola	Pronuncia	Significato
reset verbo	/ɹiːˈsɛt/	azzerare, rimettere a zero
developer sostantivo	/dɪˈvɛləpɚ/	sviluppatore, sviluppatrice
token sostantivo	/ˈtoʊkən/	simbolo, segno
essentially avverbio	/ɪˈsɛnʃəli/	in essenza
sheet sostantivo	/ʃit/	foglio
roughly avverbio	/ˈɹʌf.li/	aprprossimativamente, a grosso modo
commit verbo	/kəˈmɪt/	affidare, impegnarsi
rely verbo	/ɹɪˈlaɪ/	fare affidamento, basarsi
bug sostantivo	/bʌɡ/	cimice
implement verbo	/ˈɪmpləmənt/	mettere in pratica, attuare
icon sostantivo	/ˈaɪ.kɑn/	icona
instruction sostantivo	/ɪnˈstɹʌkʃən/	istruzione, addestramento
dash sostantivo	/ˈdæʃ/	linea
vibe sostantivo	/vaɪb/	atmosfera
directory sostantivo	/dɪˈɹɛktəɹi/	elenco, lista

I phrasal verb che sentirai

Parola	Pronuncia	Significato
end up verbo		andare a finire, finire
go through verbo		attraversare
blow up verbo		saltare in aria, esplodere
fall apart verbo		cadere a pezzi
find out verbo		scoprire
go ahead verbo	/ˌɡoʊ əˈhɛd/	procedere, andare avanti
go off verbo		esplodere
look over verbo		esaminare

Pronuncia a cui fare attenzione

Chi parla usa 78 contrazioni e forme ridotte, come don't, you're, I'm. Pronunciale nella forma breve, così come le senti.

I suoni “sh” e “zh”: essentially /ɪˈsɛnʃəli/, sheet /ʃit/, instruction /ɪnˈstɹʌkʃən/, dash /ˈdæʃ/, speculation /ˌspɛk.jəˈleɪ.ʃən/
Parole lunghe — attenzione all’accento: developer /dɪˈvɛləpɚ/, essentially /ɪˈsɛnʃəli/, speculation /ˌspɛk.jəˈleɪ.ʃən/, directory /dɪˈɹɛktəɹi/, implementation /ˌɪmplɪmənˈteɪʃən/

Come esercitarsi con questo video

Ascolta tutto il video una volta senza parlare e annota le parole che non conosci.
Inizia a velocità 0,75×, fai shadowing frase per frase e torna alla velocità normale quando diventa facile.
Registrati e confronta con l’originale, facendo attenzione a parole come reset, developer, token.

La grammatica di questo video

Le strutture che chi parla usa di più, con le parole esatte del video:

Struttura	Nel video
Forma passiva be + participio passato — conta ciò che accade, non chi lo fa	being rewritten · was just added · was added
Present perfect have/has + participio passato — un’azione passata che conta ancora adesso	I've built · it's always been · I've also heard

Cos'è la tecnica dello Shadowing?

Shadowing è una tecnica di apprendimento delle lingue supportata da studi scientifici, originariamente sviluppata per la formazione dei traduttori professionisti e resa popolare dal poliglotta Dr. Alexander Arguelles. Il metodo è semplice ma potente: ascolti un audio in inglese di madrelingua e lo ripeti immediatamente ad alta voce — come un'ombra che segue il parlante con un ritardo di solo 1–2 secondi. A differenza dell'ascolto passivo o degli esercizi di grammatica, lo shadowing costringe il tuo cervello e i muscoli della bocca a elaborare e riprodurre simultaneamente i modelli di discorso reale. La ricerca dimostra che migliora significativamente la precisione della pronuncia, l'intonazione, il ritmo, il discorso connesso, la comprensione dell'ascolto e la fluidità del parlato — rendendolo uno dei metodi più efficaci per la preparazione alla prova di speaking dell'IELTS e per la comunicazione reale in inglese.

Tecnica dello shadowing: leggi la guida completa passo dopo passo →

Pratica di Shadowing: I Spent 1.5 Billion AI Tokens on Absolute Slop - Impara a parlare inglese con i video

Scegli una modalità di pratica

Scarica l'app

I Rebuilt My Entire Website in Astro… Was It Worth It?

Is AI Doom Real... or Just Good Marketing?

/wayfinder: Nothing is too big to plan anymore

I bought the most SATISFYING TECH on the internet.

OpenAI: A Bubble Bigger Than Dotcom

The Lazy Method: How I Build $10K/Month Apps

Introducing GPT-6 Astra: the most intelligent and aligned model in the world.

Microsoft Surface vs. MacBook Air (Lab Tested)

Most devs don't understand how LLM tokens work

Modrinth Just BANNED AI Mods

An ex-OpenAI researcher just deleted language from the LLM...

I tried gaming on Linux...