Luke

Developer. Building things that actually work.

Pave CX Engineer @ Quickbase

[Quickbase Quip @quickbasequip]

good.

#cx #customersupport #customerexperience #pavetheway #quickbase

[Quickbase Quip @quickbasequip]

Welcome to Quickbase Quip! Follow for tips, tricks, product update, and news right from the Quickbase team on all our products: Quickbase, FastField, and Pave!

[Quickbase Quip @quickbasequip]

When working with Pave (or any AI tool) don't give up after one prompt! AI doesn't always get things right on the first try, but as you give more details and keep working, it'll keep getting better.

#ai #vibecoding #quickbase #pavetheway

[Quickbase Quip @quickbasequip]

Pave can create beautiful maps in your apps - and uses trusted, secure, private tools to do it, all included right out of the box.

#ai #vibecoding #saas

[Quickbase Quip @quickbasequip]

Want to see a full 30-minute demo of Pave in action? Check out our YouTube video! https://t.co/Vg3l65yERt

Pave is Quickbase's new AI app development tool that combines the speed of AI and the security, privacy, and governance of Quickbase. Free trial link in the video!

[Quickbase Quip @quickbasequip]

When working in Pave - trust the agent! Give the chat all the details of what you're looking for, and keep chatting and giving it feedback!

...Wait, did I accidentally give relationship advice in this tech video?

[The Neuron @theneurondaily]

Every business has one spreadsheet doing way too much.

Customer notes. Follow-ups. Project status. Color coding. Mystery tabs only one person understands.

In this episode, @CoreyNoles and @TheNeuronScribe test whether Pave by @Quickbase can turn that messy spreadsheet into a real internal app. 🧵

[Luke @JodiceLuke]

we live in the era where tokens are the real currency for creativity

[Luke @JodiceLuke]

This is the next gen for AI.

Looking forward to the further Case/Feedback Triage assistance

[Walden @walden_yan]

My take 24 hours after Fable 5:

Your organization will likely not scale with the exponential curve of AI.

I'l just come out to say: This should be a wakeup call for engineering teams.

Set up your cloud software factories. Now.

Models can now fix impossible bugs, UI-test the hardest flows, writing extremely good code, etc. I have't opened Datadog manually as far as I can remember.

AI should be the first-line defense for bugs and feedback. Humans should only look at PRs after an AI has already reviewed it. AI should generate screen recordings of any PR before a human eye even reaches it. The agent should just prompt itself most of the time.

Ex. (pictured) our ui feedback channel manages itself, creates tickets, assigns itself automatically

You might also be worried about cost. Anthropic, OpenAI, and other labs will likely continue to put out bigger and more expensive models. But, we will also continue to get more capable small models. Not everything will need the smartest models. It's about having the organizational harness in place to continue taking advantage of this rising tide.

Moreover, if you use Devin, we've already optimized our harness a bit, and Fable is actually only ~40% more expensive in practice (vs the 2x people assume). I'm honestly pleasantly surprised - it might be higher ROI than you think.

Anyway, if you take anything away, engineers shouldn't be manually picking up tickets, humans shouldn't be digging into logs themselves, rethink what you do with your time that shouldn't just be an AI. We need to rethink what humans spend their time going.

[Walden @walden_yan]

My take 24 hours after Fable 5:

Your organization will likely not scale with the exponential curve of AI.

I'l just come out to say: This should be a wakeup call for engineering teams.

Set up your cloud software factories. Now.

Models can now fix impossible bugs, UI-test the hardest flows, writing extremely good code, etc. I have't opened Datadog manually as far as I can remember.

AI should be the first-line defense for bugs and feedback. Humans should only look at PRs after an AI has already reviewed it. AI should generate screen recordings of any PR before a human eye even reaches it. The agent should just prompt itself most of the time.

Ex. (pictured) our ui feedback channel manages itself, creates tickets, assigns itself automatically

You might also be worried about cost. Anthropic, OpenAI, and other labs will likely continue to put out bigger and more expensive models. But, we will also continue to get more capable small models. Not everything will need the smartest models. It's about having the organizational harness in place to continue taking advantage of this rising tide.

Moreover, if you use Devin, we've already optimized our harness a bit, and Fable is actually only ~40% more expensive in practice (vs the 2x people assume). I'm honestly pleasantly surprised - it might be higher ROI than you think.

Anyway, if you take anything away, engineers shouldn't be manually picking up tickets, humans shouldn't be digging into logs themselves, rethink what you do with your time that shouldn't just be an AI. We need to rethink what humans spend their time going.

[Muhammet A. 👉🏻 Mobile Dev @indiesoftwaredv]

This is my loop

I built a SaaS that posts to Instagram + TikTok 24/7

I don't write the captions. I don't pick the music. I don't touch it

The stack that runs it while I sleep:

> PHP 8.3, no framework
> Caddy web server
> SQLite in WAL mode
> Cloudflare R2 for video storage
> Cloudflare Tunnel, no open ports
> Stripe for billing
> OpenAI writes every caption
> ffmpeg muxes the music
> Zernio publishes to IG + TikTok
> Vanilla JS + CSS on the front
> one cron job that loops forever

No Next.js. No Kubernetes. No VC

[Luke @JodiceLuke]

thinking about giving Zig a try in the big 26

[Kristof @CoastalFuturist]

BREAKING NEWS: God joins Anthropic as member of technical staff

[Isaac Sacolick @nyike]

Time to first production app - a primary KPi at @Quickbase

“Pave is a return to how we’ve always been.”

#Empower26 #AI

[GitHub @github]

We are investigating unauthorized access to GitHub’s internal repositories. While we currently have no evidence of impact to customer information stored outside of GitHub’s internal repositories (such as our customers’ enterprises, organizations, and repositories), we are closely monitoring our infrastructure for follow-on activity.

[Isaac Sacolick @nyike]

I'm looking forward to leading the closing keynote @Quickbase Empower, May 19-20 in Houston. Who's ready to Pave their way to the #AI future?

https://t.co/MTx6ReVXDU

[International Cyber Digest @IntCyberDigest]

‼️🚨 UPDATE: The TanStack npm attack is now a full campaign.

'Mini' Shai-Hulud has hit:
- OpenSearch
- Mistral AI
- Guardrails AI
-UiPath
- Squawk packages across npm and PyPI

The malware specifically targets AI developer tooling. It hooks into Claude Code (.claude/settings.json) and VS Code (.vscode/tasks.json) to re-execute on every tool event, long after the infected package is gone. npm uninstall does not fix this.

[Luke @JodiceLuke]

@Spotify Looks like we have some container issues with the new Prompt playlist gen

[Mnimiy @Mnilax]

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens.

in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt:

- the 14% you lose to CLAUDE.md before typing a word
- the 13% you pay re-reading old chat history
- the 11% from hooks you forgot you installed
- why most "Claude got dumber" complaints are wrong

if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7.

instead of another show tonight, watch this.

my own breakdown based on 400+ hours of usage is below, read it after the podcast

[Adrían Bridgwater✍⌨️ @ABridgwater]

Quickbase's Pave targets vibe coding's notorious 80% problem: https://t.co/OtnqmQpqxS ____ @thenewstack