Broden

Indie Developer who loves making Multiplayer Games and creating Web Apps. 10+ years Unity experience. ServiceNow CSA Certified. He/Him, opinions are my own

[Ramp Capital @RampCapitalLLC]

I think millennials are the real AI sweet spot. Digital natives with just enough experience to prompt well and sanity-check the output.

Gen Z is too inexperienced and trusts AI like it’s gospel.

Gen X is trying to make it to retirement without learning another interface.

Boomers are still googling how to convert a pdf.

[Future Stacked @FutureStacked]

Ok Google NanoBanana is insane.

People are unlocking new creative ways to use it.

10 wild examples:

[DAN KOE @thedankoe]

I get unnecessarily mad when people don't stick to their goals.

You say you want to start a business, lose weight, meet new people, whatever. You say you want to change your life because you're tired of where you are.

Someone tells you exactly what to do, gives you the entire roadmap.

Then you don't do it. And you can't give any good reason why.

"Oh I have to work and got sidetracked."

"I didn't go to the gym because I had something else do to."

What the fuck are you talking about?

You say you "have" to work and "have" to do whatever else you're doing in the life you just said you don't want to live, but you don't HAVE to do the only things that lead to the life you want?

Everyone is obsessed with getting "actionable advice" when that clearly doesn't matter at all. Your psychology is in the toilet. Your priorities are nonexistent. You need to take a day off and really think about what you are doing.

"Oh Dan be more empathetic!"

That IS empathy. Empathy is wanting the best for someone even if it hurts their little feelings. Most people will simply pander to you so that they feel good about not making you feel bad. That's nowhere close to empathy.

Do better.

[signüll @signulll]

the reason why people abandon so many “almost done” things is because the last 20% of anything is friction, detail, & accountability.

that last 20% of the work doesn’t feel like 20% at all, it feels like the whole damn thing & then some.

this is especially true in an ai era where you can go from zero to something so quickly.

[Broden @brodengunn]

@_HMSP @lildickytweets

[Inan Evin @inanevin0]

🧵 1 / 4
I made an open-source AI system that mimics human directors. E.g. it shoots your in-game cut-scene just like how Quentin Tarantino would. Implemented on #unity3d , accepted into #chiplay2022 @acmchiplay

#indiegame #videogame #cinematography #IndieDevs #gamedev

[OpenAI Developers @OpenAIDevs]

We’ve put together a reference implementation for building and orchestrating agentic patterns using the Realtime API. You can use this repo to prototype a voice app using multi-agent flows in less than 20 minutes!

https://t.co/YdGZGt2Y6q

[Akshay 🚀 @akshay_pachaar]

Don't do RAG!

Imagine loading all the relevant documents into your model before you ask a single question—no more waiting on real-time retrieval or dealing with complicated retrieval pipelines.

This is precisely what CAG does, and it does so remarkably well!

The core idea is to replace real-time document retrieval with preloaded knowledge in the extended context of LLMs. This approach ensures faster, more accurate, and consistent generation by avoiding retrieval errors and latency.

(refer the image below as you read)

Key advantages:

↳ No Latency: All data is preloaded, so there’s no waiting for retrieval.

↳ Fewer Mistakes: Precomputed KV-cache avoids ranking or document selection errors.

↳ Simpler Architecture: No separate retriever—just load the cache and go.

↳ Faster Inference: Once cached, responses come at lightning speed.

↳ Higher Accuracy: The model processes a unified, complete context upfront.

But it also has two major limitations:

- Inflexibility to Dynamic Data
- Constrained by Context Length of LLM

Hope you enjoyed reading!

For those who want to dig more, I've shared link to the CAG paper in next tweet!
_____
Find me → @akshay_pachaar ✔️
For more insights & tutorials on AI and Machine Learning.

[Broden @brodengunn]

@gamesplusjames would love you to do a 2025 refresh on "Unity 2 Player Tutorial" which to this day is still my #1 recommended resource for new Unity Devs. It's short, it covers the fundamentals without getting lost in detail, it's short enough not to be intimidating. Love it.

[OpenAI @OpenAI]

Some favorite posts about OpenAI o1, as selected by researchers who worked on the model 🧵

[Adam.GPT @TheRealAdamG]

Developers, developers, developers.

[Simon Willison @simonw]

Hidden at the bottom of this announcement:

"By switching to the new gpt-4o-2024-08-06, developers save 50% on inputs ($2.50/1M input tokens) and 33% on outputs ($10.00/1M output tokens) compared to gpt-4o-2024-05-13."

That's a pretty substantial price decrease!

[Youmio @youmio_ai]

🚨 Introducing 'Dreamia'🌱

Watch the full keynote from @mike_mrkite at NFC Lisbon now to discover how our cutting-edge AI character engine is designed to revolutionise how players interact with NPCs in virtual worlds.

What do you think?

We'd love to hear your thoughts below👇

[Alamin @iam_chonchol]

Google Maps received a HUGE update.

Now, you can message directly just like ChatGPT.

Here are 7 WILD examples:

[Abhishek @HeyAbhishek]

ChatGPT can now create Flowcharts and Diagrams.

No more wasting hundreds of hours creating visuals for presentations or research papers.

Here’s how to do it for free in a few minutes:

[Poonam Soni @CodeByPoonam]

1/ Google Lens in Chrome desktop

You’ll be able to easily select, search and ask questions about anything you see on the web, all without leaving your current tab.

[ao @aoTheComputer]

https://t.co/H12UmsDvsg

[Arweave India @arweaveindia]

MVP in action

[arweave.com @aoTheVentures]

1/ First ao Ventures Cohort Presents at Demo Day 🧵

Here’s a quick look at each innovative project 👇

[ao @aoTheComputer]

At the recent AO Summit in Charleston, @samecwilliams, Founder of Arweave and CEO of @fwdresearch, delivered an insightful talk about the creation of ao and his own journey in computer science. 💻

Watch the entire talk here. 👇