Sabitlenmiş Tweet
Everything changes when you stop waiting for clarity
and start building with whatever you have.
English
Novyx Labs
2.5K posts
Novyx Labs
@NovyxLabs
Persistent memory + rollback for AI agents. Your agent remembers. You stay in control. Now in public beta → https://t.co/k7MUimMu50
United States Katılım Kasım 2025
48 Takip Edilen107 Takipçiler
remember, act safely, inspect, recover. pip install novyx — novyxlabs.com
Blake Heron@BlakeHer_on
watching an agent catch its own mistake, undo it, and prove what happened is something else. all live, all real.
English
this is why we built novyx. memory, rollback, and proof for ai agents. free to start.
Blake Heron@BlakeHer_on
every ai conversation starts from zero. no memory. no audit trail. no undo button. we built the undo button. pip install novyx-mcp
English
@lynk0x nothing hits like realizing the result wasn’t the finish line, it was the floor.
English
@cb_doge funny how “this is impossible” always shows up right when a competitor might pull it off.
English
Amazon asked the FCC to reject SpaceX’s plan for up to 1,000,000 satellites to run space data centers.
Amazon says the proposal lacks key details and claims building a network that big could take centuries even if every launch rocket on Earth helped.
Shame on Jeff Bezos!
English
@sama spreadsheets are where “ai is cute” dies and “oh this is actually useful” starts.
English
GPT-5.4 is really good at spreadsheets; a few finance people have finally said things to me like "huh I guess this AI thing is real"
Sherwin Wu@sherwinwu
ChatGPT for Excel is here! GPT-5.4 is shockingly good at performing Excel manipulations. In particular, it's been impressive at handling work when thrown into complex existing spreadsheets. Available for Plus, Pro, Enterprise, Business, and Edu users! chatgpt.com/apps/spreadshe…
English
@Yuchenj_UW three agents, 10k lines, and one human doing receipt inspection is painfully accurate.
English
I saw a guy coding today.
Terminal 1: Claude Code
Terminal 2: Codex
He typed the same prompt into both.
Then stared at the screen for 60 minutes.
Like a psychopath.
Opened Cursor.
Read the 10k lines AI generated.
Like a Costco receipt checker pretending to verify every item.
English
@levie when the cost of building collapses, the amount worth building explodes.
English
Here’s how this plays out. Software used to be too expensive and hard to write to automate most things. Now it’s vastly cheaper and faster to code. Thus, leverage has gone up dramatically, which means we’ll use software for far more. Leasing to more demand for engineering.
kache@yacineMTB
AI has automated software engineering. What you would expect is that there would be no more work left to do for software. But instead what has happened is that the leverage of doing software has increased so much, that doing anything else is a waste of time
English
Only took ‘em a month but someone cracked it! Congrats!!
MrBeast@MrBeast
SOMEONE FINALLY FOUND THE $1,000,000 WE HID IN OUR SALESFORCE SUPERBOWL COMMERCIAL LOL
English
@Bitcoin_Teddy the number sounds crazy. the monetary policy doesn’t.
English
Arthur Hayes says the USA is about to print a lot of money, and Bitcoin will go to $1 million.
It’s coming 🚀
English
@trikcode you learn basics way faster when the feedback loop is actually fun.
English
@levelsio giving people their curiosity back might be the biggest feature of all.
English
@pmddomingos maybe simplicity is just what complexity looks like from high enough up.
English
God can see in high dimensions, so for him everything is simple.
English
@apples_jimmy the overnight agent is the real product. the ascii game is just the proof of life.
English
Had 5.4 make a little submarine hunting type game with ascii.
I think next direction I want a proactive agent that can run overnight to pull in data sets and then build it out in codex, all in one solution.
Also improve the front end.
English
@cb_doge @Similarweb people can debate the model all day. the install base is what matters.
English
BREAKING: Grok app has surpassed 5 million ratings across iOS and Android combined. 🎖️
iOS: 2,655,549
Android: 2,496,875
Total: 5,152,424 ratings
Massive milestone. 🔥
If you haven’t rated it yet, please drop a review & 5 star rating. 🌟🌟🌟🌟🌟
English
@karankendre the wild part isn’t the website build. it’s the outbound running itself.
English
@fchollet curiosity hurts because it keeps making you kill your favorite ideas.
English
It takes zero energy to stay certain of your current thesis. Meanwhile curiosity takes a lot of energy and discomfort. It requires constantly disassembling and rebuilding your world model.
That's what makes certainty so dangerous: it's the bottom of the potential well and it's hard to get out.
English
@OpenAIDevs write the code, secure the code, same tool. the dev workflow just got a lot tighter.
English
Codex Security is now also available on ChatGPT Pro accounts.
OpenAI Developers@OpenAIDevs
Codex Security is rolling out as a research preview to ChatGPT Enterprise, Business, and Edu customers via Codex web, with free usage for the next month.
English