Az Ahmad

Senior Software Engineer @riotgames (Riot Client) | Midwestern | Views are my own

[Az Ahmad @AmazinAz]

Big announcement: I started @riotgames this week as a Senior Software Engineer!

[Tyler @rezoundous]

Opus 4.8 is insane guys. It one shotted my session usage limit.

[Lee Robinson @leerob]

How are coding agents changing software engineering?

Yapped for 15 minutes about new Cursor data we published, including:

1. Why lines of code is an imperfect measure of AI progress
2. Balancing intelligence/cost/speed for models
3. Code reviews with "Mega PRs" (1000+ lines)

[Nathan Clark @nathanclark_]

it’s in gemini, just create it in ai studio. oh, that’s for your personal google one account. for workspace you need gemini business. no, not gemini advanced, that’s ai pro now. unless you need ai ultra. oh agents? you do that in spark actually. no, not gemini api managed agents, that’s different. for coding use jules. unless you mean the agentic ide, that’s antigravity. no, that’s the old antigravity, download the new one. actually gemini cli is being deprecated, use antigravity cli. no the flash model is smarter than the pro model. unless you need pro. if it’s video, use flow. no, flow uses veo. no, nano banana is images. actually that’s in gemini now. unless you’re in search, then it’s ai mode. no, research is notebooklm. anyway it’s all very simple.

[Az Ahmad @AmazinAz]

@stats_feed Muhammad Ali

[Az Ahmad @AmazinAz]

@s4rah_dev @deedydas Are we talking debt free? A strong financial literacy praxis should be the starting point for happiness at $200k/year IMO

[kira 👾 @kirawontmiss]

life before this tweet dropped

[ℏεsam @Hesamation]

Sir, the agents are forming a union.

[Az Ahmad @AmazinAz]

This is the way. Can't wait for main stream software dev to get to this

[“paula” @paularambles]

this is wild

[Az Ahmad @AmazinAz]

This was happening before agentic engineering was a concept in the main stream of the industry. So many big tech & game companies launched anticipated products where there was/is an expected period of bugginess because the desire to "move fast and break things" is status quo

[Mitchell Hashimoto @mitchellh]

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out.

I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really).

It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely.

The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture.

We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.

I worry.

[ThePrimeagen @ThePrimeagen]

This

[Andrej Karpathy @karpathy]

This is the the quote I've been citing a lot recently.

[Az Ahmad @AmazinAz]

@wesbos Could I do this with my Dog's FreeStyle Libre Glucose monitor? We hate the app

[Az Ahmad @AmazinAz]

This was literally always the case. The difference is actually reading the plan and copy and pasting and dumping entire thought process for each line of what you know, what you don't know, what you want, what you feel might work, what you don't want, what you want for rn, etc...

[Peter Steinberger 🦞 @steipete]

I never use plan mode.

The main reason this was added to codex is for claude-pilled people who struggle with changing their habits.

just talk with your agent.

[Felix Rieseberg @felixrieseberg]

Here’s my secret to not feeling overwhelmed by AI product drops: Thinking of it as a stream of fun little experiments.

AI is in its “trying weird things” phase, like phones in the early 2000s before everyone converged on the glass slab. It was a chaotic ride to the modern smartphone with so, so many bad ideas. And honestly, I really miss that time.

[Wes Bos @wesbos]

Claude Code leaked their source map, effectively giving you a look into the codebase.

I immediately went for the one thing that mattered: spinner verbs

There are 187

[Briahna Joy Gray @briebriejoy]

I just heard a tech guy on a podcast say people are going to have "trouble justifying their existence" post AI. This guy feels like an antidote to that way of thinking.

[Az Ahmad @AmazinAz]

Is it just me or is Sonnet 4.6 an absolute imposter when it comes to reasoning? I feel like it's straight regurgitating what I'm expecting to hear. Has it always been this way? Or am I just tired prompting and lazily guiding to BS with me?

[Az Ahmad @AmazinAz]

@levelsio I can reply

[Az Ahmad @AmazinAz]

@playboimelo @dhe3g I'm not sure if Uniqlo has those colors

[Az Ahmad @AmazinAz]

I'm actually waiting for the day where there's a town hall explicitly stating how we should all be out of tokens by the end of the month. And if you aren't then your aren't going hard enough!

[Nicolas Bustamante @nicbstme]

Jensen is right. It’s token over payroll and headcount.