Daniel Young 🫰🏻

@Rengle820 Automated testing will play a big role, but companies are 10 years behind on automated testing and making that codebase testable requires a rewrite. We’re trying to adopt and move towards more AI coding but when your testing pyramid is inverted, it’s too hard lol.

The next big question to ask the engineering org is: What needs to happen so you can trust AI generated code without having to review every line. Orgs that can setup a system that doesn’t require manual review will have a huge advantage.

I post all my monthly projects on LinkedIn and had such an amazing conversation with this person after they downloaded my app. It’s beyond cool to be able to impact even one person this way. I love merging tech with golf and can’t wait to share my next one; It’s a banger.

@Rengle820 A 24 That plays a gts2 apparently

The real AI video benchmark we need is to give each generated golf swing a handicap. This is Gemini Omni, and I'm giving it a 24.

How did we get to the point in golf course design where there are literally no trees off the fairway to penalize a missed fairway…so boring to watch.

Finally sharing my April project: Cue. Most golf apps fix your swing but once you can strike it, scoring comes down to what’s between your ears. Cue uses LLMs to deliver quick, personalized tips for on the course. Give it a try next round: apps.apple.com/us/app/cue-a-g…

@levelsio It’s clearly trainee on engineers over estimating how long work will take to cover their asses ;)

My Claude keeps saying "that's a day of work" when it's like done in 5 min 😂

@sairahul1 They’re in different categories running at scale my guy. The hardware requirements to run VibeVoice and Whisper V3 turbo are in different leagues (9b and 800m). VibeVoice also runs other LLMs (Qwen) under the hood for formatting. VV is amazing, but you can’t really compare them.

OpenAI Whisper API: $0.006/min → $0.36/hr ElevenLabs Speech-to-Text: $0.40/hr Deepgram: $0.0043/min → $0.26/hr AssemblyAI: $0.37/hr VibeVoice ASR: $0/hr 50+ languages. Full diarization. One pass. Microsoft just ended an industry.

@Thetimmac Resell em when that pipeline opens up.

@DanimoYoung I got handball semi-final tickets, electric factory.

The price on these Olympics tickets is fucking criminal

@nbaschez People run into this loop all the time too! Don’t let perfection be the enemy of good and just ship.

My biggest challenge with vibe coding / agentic engineering lately has been getting stuck in what I call a "plan doom loop" - have AI write a plan - review myself, seems good - have AI review plan, it always finds something - repeat It drains my time and energy to determine how important the "findings" really are Who has solved this

@jxnlco It’s so awesome that you’ve navigated this. Always been in awe of your abilities, even while waiting to take our stats midterms. Looking forward to keeping up with your journey!

Wow I just realized I passed 50,000 followers For those who don't know me, I used to be a machine engineer. In 2021 I had a pretty serious hand injury, like an enemy, from doing any kind of work, let alone tying my shoes or cooking food for myself. I thought my life was over. My identity was someone who made things and wrote code and worked hard. I had a lot of my personal values tied to my ability to make things and be smart and apply force onto the world But I lost that not because of AI replacing me but because my hands just didn't work anymore Then near the end of 2022, OpenAI Released ChatGPT as well as the Whisper models The first time not completely though, I can make things again if I just sort of slowly copy-pasted code from ChatGPT into PyCharm I could dictate a little bit better and almost get some work done The next AI wave was happening but I still knew that I couldn't really join a startup. I would turn down recruiting calls and calls with founders because I knew that this wasn't enough I still wouldn't be able to work even four or five hours a day if I had to use a computer the way that I did then. But in many ways coding agents change that I went from someone thinking that my technical career was over to starting a consulting business, finding leverage, teaching people, and helping get businesses but there is no more proof that coding agents work than the fact that I literally was able to join OpenAI to help others see what is possible I literally went from thinking my career was over not because I was being replaced by my AI but because the fact that my body is failing to use ChatGpt to re-enable myself to make things and now using Codex literally at OpenAI I feel like I already did the hard work of not tying my identity to my intelligence or to my ability to write code And that way I got lucky. I've adopted voice coding and AI coding sooner than everyone else not because I was some kind of trailblazer but because it was the only thing I could do Now I gotta do that here on such a huge stage. Only getting started

@gchorba I think that’s the next big fad Gene; will force them to happen fast. No dillydallying allowed

It’s weird how little quicksand and how many meetings adulthood involves

@schrockn What’s the opportunity cost of having your sr and staff engineers review 4k line reviews that these tools spit out?

15-25 usd per review my lord.

@LouStagner I’m curious about vanity indexes for….purposes and I’m curious if you have any data on it. @USGA has the probability of negative score differential, but nothing on positive.

@kylegawley Code output isn’t the bottleneck; it’s solving the right problems.

vibe coders will never understand that 10x devs can code faster than AI models

@boxmining This is why I love firebase so so SO much. Handles a lot of it and you don’t even need to handle any infra.

Vibe coding is easy until you’re hit with: - auth - security - workflow logic - context windows - confirmation emails - payment integration And then you wish you knew how to code.

@ryancarson It’s cheap compared to an engineer, but it’s rubbing people the wrong way because not most orgs operate in reverse; your high impact sr people spend time reviewing code while more jr write code. The industry isn’t quite ready for this, yet.

I honestly don't understand why people seem to not grasp why $20 for a great code review is cheap

@dexhorthy Just make a new agent to train your old agents at finding bugs better.

Here’s what’s gonna happen: - you replace your code review with feedback loops (sentry, datadog, support tickets, etc) - you stop reading the code - software factory fixes everything - one day something breaks at 3am, agent can’t fix it - nobody’s read the code in 3 months - you have 3 weeks of downtime trying to re-onboard and fix it - you lose significant % of your contracts and users - your company is now dead

@theo “You’re absolutely right, $15-$25 per review is absolutely insane. I’ll fix that right now”

Anthropic really needs like 1 normal person to proof these things before posting

@weswinder You can just use electron and compile all your web apps into a desktop app if you want to stay in the same stack! Even things like capacitor exist to turn your web apps into mobile apps, albeit running in a web view.

stop building web apps start building desktop apps trust me