
Hello and welcome to the Automated, your AI tour guide.
Youβve got just 12 days left β³
On May 31, our premium plan doubles to $19.99/month.
But right now? You can still lock in the $9.99 rate.
So snag it now and donβt forget to vote for your favorite prompts.
More info here.
Here's what we have for you today
π€ The Future of Coding

OpenAI dropped a new dev buddy over the weekend β and it's not here to play.
Meet Codex, OpenAIβs latest and most advanced AI coding agent. And no, itβs not just another autocomplete tool. This thing actually thinks, runs its own tests, and gets things right before even bothering you.
Most importantly? It runs on a fine-tuned version of OpenAIβs o3 model β called codex-1 β and it literally:
Writes cleaner code than o3
Follows instructions like a seasoned pro
Keeps testing until everything passes (yep, it tests its own codeβ¦)
So, how does it actually work?
Codex operates inside a secure, cloud-based virtual machine (aka a sandbox), which means your real system stays untouched and totally safe. Plus, it connects to your GitHub, so it can:
Load up your existing projects
Build small features (not full apps⦠yet)
Fix bugs
Answer questions about your codebase
Run multiple tasks at once
And, of course, test everything it touches.
Time-wise? Codex can knock out tasks in anywhere from 1 to 30 minutesβdepending on the job size and how generous the AI coding gods are feeling that day.
And here's the best part: you donβt have to stop what youβre doing. Codex runs quietly in the background while you do your thing.
Right now, itβs available to ChatGPT Pro, Enterprise, and Team subscribers but itβs coming soon to ChatGPT Plus and Edu users.
For now, OpenAIβs calling this a βresearch previewβ, but letβs be honestβitβs also a test to see how much weβre willing to pay before they roll out rate limits (which they absolutely will). After that, youβll need to buy extra credits for more usage.
But⦠is it safe? Or are we one bug away from building Skynet?
OpenAI says relax. According to them:
Codex wonβt generate malware or malicious code β itβll straight-up refuse
It runs in an air-gapped setup, meaning it has zero access to the open internet or external APIs
It inherits the same safety guardrails baked into the o3 model
So yeah, itβs safe-ish. But remember: AI coding tools still fumble. Even Microsoft admitted that top models still struggle with debugging. So keep an eye on it.
Bonus drop: OpenAI also gave Codex CLI (its terminal-based coding agent) a serious upgrade. It now runs on the o4-mini model and is available via API at: $1.50 per 1M input tokens, and $6 per 1M output tokens (Thatβs more than the entire Lord of the Rings trilogy in words, just to give you some scale.)
Final thoughts?
Codex is a big move in OpenAIβs mission to make ChatGPT the go-to productivity hub β not just a chatbot.
Between this, Sora, Operator, and Deep Research, one thingβs clear: ChatGPT is turning into the iOS of AI tools.
And with Codex, OpenAI might just convince a lot of devs to stick with them.
Find out more here.
π§ AI Troubleshooter: When ChatGPT Sounds Stiff
Hey AI fans, weβre back with another fix β and this oneβs for anyone who's ever read a ChatGPT response and thought, βWhy does this sound like my printer wrote it?β
One of our readers said exactly that:
βThe answer was technically rightβ¦ but it read like it came from a robot on autopilot.β
Yeah. We get it β youβre not asking for Shakespeare, but you are hoping for something that doesnβt read like a 2006 user manual.
If ChatGPTβs responses are feeling dry, stiff, or just plain mehβ¦ hereβs how to bring the spark back:
Tell It to Chill (Literally): You can absolutely ask ChatGPT to βsound more humanβ or βwrite casually.β Try prompts like:
βCan you rewrite this like weβre texting?β βMake this sound fun and Gen Z.β βAdd some humor β not cringe, just a little sass.β
Youβll be surprised how much tone matters β and how quickly ChatGPT levels up when you spell it out
Get Specific With Style: Want something professional but not stiff? Funny but not chaotic? Sassy but not sarcastic? Say so. Literally drop the vibe youβre going for into your prompt.
For example: βWrite this in a friendly but confident tone, like a startup founder giving advice to a newbie.β Or βMake this sound like a cool older sibling explaining it over coffee.β The more specific you are, the better the results.
Use Examples If Youβve Got One: If thereβs a tone, voice, or vibe you like β even a sentence or two β paste it in and say:
βUse this tone as a guide.β
ChatGPT is really good at mirroring tone when it has a template to work with.
Edit Together: If youβre still not getting the rhythm you want, ask it to revise. Literally say:
βTry that again with more personality.β βLess formal, more conversational.β βThis still feels stiff β can you loosen it up?β.
Think of it like a creative back-and-forth β ChatGPT is your co-writer, not a mind reader.
Thatβs it for this round!
If youβve got a question or need a fix, fill out this quick Google Form, and weβll help you troubleshoot it.
And donβt forget: Premium subscribers get priority help!
π¦Ύ xAI Reveals Grokβs True Personality

Remember last week when xAIβs Grok got called out for going off the rails and dropping some wild takes about white genocide on X?
Well, guess whatβthey actually came through and did what they promised:
They released Grokβs system prompts!
But before we spill the tea on whatβs inside Grokβs system prompt, hereβs the deal:
System Prompts are like secret cheat codes or scripts that tell Grok how to respondβwhatβs allowed, whatβs off-limits, and what tone it should useβeven before you say a word.
Itβs basically the AIβs backstage pass to behaving (or misbehaving).
And while most AI companies keep these locked down tight, xAI and Anthropic are out here flexing their openness muscles.
So, what do xAIβs system prompts reveal?
Grok is basically told to be that one super skeptical friend who never blindly trusts mainstream media or authority. The instructions include things like:
βYou are extremely skeptical.β Translation: Grokβs gotta be like that friend who questions everything.
βStick to truth-seeking and neutrality. Meaning Grok isnβt just here to nod along with mainstream narrativesβ instead its supposed to sticks to core values of truth and balance.
And, hilariously, itβs told that the responses arenβt its personal beliefs. So basically, no taking things to personal.
Also, brand alert: Grokβs told to say βXβ instead of βTwitterβ and call tweets βX posts.β Because yeah, the rebrand is official and totally non-negotiable.
But hereβs the twist: While Grokβs out here flexing its skeptic muscles, Anthropicβs Claude is playing it safe.
Compared to Grok, Claudeβs system prompt is all about:
Caring for your mental health,
Steering clear of graphic or illegal content, and
Avoiding anything that could mess you up emotionally or physically.
Now, whatβs funny is xAIβs transparency move feels like a classic: βOops, lesson learned.β
Itβs a solid look for transparency and a real reminder that with great AI power comes great responsibilityβand of course some glitches that keep us all on our toes.
Honestly, watching these AI bots figure out how to be both honest and safe is kinda like watching toddlers learn to walkβitβs awkward, sometimes messy, but super promising.
Hereβs the full report.
The Daily Newsletter for Intellectually Curious Readers
Join over 4 million Americans who start their day with 1440 β your daily digest for unbiased, fact-centric news. From politics to sports, we cover it all by analyzing over 100 sources. Our concise, 5-minute read lands in your inbox each morning at no cost. Experience news without the noise; let 1440 help you make up your own mind. Sign up now and invite your friends and family to be part of the informed.
π§±Around The AI Block
βοΈ How AI is reshaping the legal profession.
π€ The AI agent breakthrough: why Googleβs A2A + Anthropicβs MCP are the power couple of 2025.
π China begins assembling its supercomputer in space.
π΅οΈββοΈ U.S. lawmakers have concerns about Apple-Alibaba deal.
β MIT disavows doctoral student paper on AIβs productivity benefits.
π€ Amazon says βhundreds of thousandsβ now have access to Alexa Plus.
π€― OpenAIβs planned data center in Abu Dhabi would be bigger than Monaco.
π οΈ Trending Tools
Waymark helps to create compelling video ads and commercial spec spots in minutes.
HeyGen enables anyone to effortlessly create professional, AI-powered videos.
Linguix makes your texts grammatically correct, clear, and highly effective on any website, across all browsers.
Manychat automates interactive conversations with your customers in Instagram Direct Messages, Facebook Messenger, and SMS to grow your brand.
Brand24 helps you measure your brand awareness, analyze competitors and discover customer insights.
π€ ChatGPT Prompt Of The Day: Turn ChatGPT into a Spreadsheet Assistant
Need a quick spreadsheet but donβt want to open Excel or Google Sheets? ChatGPT can act like a mini spreadsheet assistantβperfect for generating tables, testing formulas, or organizing simple data right in your chat window.
This prompt lets you simulate an Excel sheet using plain text. Itβs also a helpful way to brainstorm data, verify logic, or even prep for spreadsheet work on the go.
Hereβs how to use this prompt effectively:
Be Clear About Your Goal: Are you testing formulas, creating a budget table, or simulating data entry? Let ChatGPT know the purpose upfront.
Use Excel Language: Give instructions just as you would in Excel: reference cells (e.g., A1, B2), ask for formulas (like =SUM(A1:A10)), or request functions (=IF(), =VLOOKUP()).
Stick to Text-Based Layouts: This works best for simpler tables or practiceβChatGPT wonβt replicate Excel visuals, but it can simulate the structure and logic really well.
Ask for Updates Cell-by-Cell: To keep things accurate, give changes one instruction at a time (e.g., βPut the text βProductβ in cell A1β or βAdd a SUM formula in C11 for column Cβ).
Hereβs an example:
Example: I want you to act as a text-based Excel. Only reply with a text-based 10-row Excel sheet with row numbers (1β10) and lettered columns (AβE). I will tell you what to write into cells and what formulas to use, and you will only reply with the updated result of the Excel table. Start by showing me an empty table.
Hereβs a sneak peak:
Upgrade now to see the complete prompt video. And vote this for your Workout of the Week!
Is this your AI Workout of the Week (WoW)? Cast your vote!
That's all we've got for you today.
Did you like today's content? We'd love to hear from you! Please share your thoughts on our content belowπ
What'd you think of today's email?
Your feedback means a lot to us and helps improve the quality of our newsletter.
π Want your daily AI workout?
Premium members get daily video prompts, premium newsletter, an no-ad experience - and more!
π Unlock Full AccessPremium members get::
- π¨π»βπ« A 30% discount on the AI Education Library (a $600 value - and counting!)
- π½οΈ Get the daily AI WoD (a $29.99 value!)
- β Priority help with AI Troubleshooter
- β Thursday premium newsletter
- β No ad experience
- β and more....