hi

Turn your business data into dashboards at manually for now until it’s fully automated)

[Movez @0xMovez]

Google engineer:

"In 2026 if you aren't building AI agents it's crazy how behind you are

at Google, 85% of our engineers were running self-improving agentic loops & graphs"

in this 32-minute talk a Google engineer reveals how the future of agentic coding will look

worth more than 10 paid agentic courses

watch today, then explore how to build self-improving agents with graphs in article below

[hi @nerdorgeek]

@ctarocker @CW8900 😂😂😂

[hi @nerdorgeek]

@HyerRoad @AkshayNarisetti idk anything about this, but do you know why they made hardware as opposed to an app?

[hi @nerdorgeek]

@KobeissiLetter it’s a value play, just don’t know what they’re thinking. Probably AI

[hi @nerdorgeek]

@thsottiaux @anshgrows don’t listen to him!!!

[hi @nerdorgeek]

@DevJuyoung @GFYS2023 Do you have any ideas how realistically a SaaS can utilize a token as a competitive advantage (front or backend)?

I’m building a B2B SaaS using Codex rn basically that when people upload/connect data, they get a dashboard that they get to keep and bring it back for edits.

[hi @nerdorgeek]

@thsottiaux If u reset under 10 hours, pls release ultrafast mode at the same time lmao

[hi @nerdorgeek]

@WatcherGuru $DEVC on #PulseChain, let’s goooo!!!

[hi @nerdorgeek]

@Saccc_c I must’ve been unflagged a few days ago phew!

[hi @nerdorgeek]

@m0nkeypantz @thsottiaux ah, didn't know that. thanks

[hi @nerdorgeek]

@HoloMapper @thsottiaux what the. thanks for sharing

[hi @nerdorgeek]

@m0nkeypantz @thsottiaux nah bro that'll waste my usage lol
it's in chatgpt's normal chat

[hi @nerdorgeek]

@muchuan_lin I really like and will continue using the product despite being throttled.
But personally, I’ve experienced around 80-85% limit reduction on 5.6 compared to last month

[hi @nerdorgeek]

@thsottiaux Make it where my weekly limit doesn’t last longer than my monthly 20x sub pls

[hi @nerdorgeek]

@rishabhjoshii can I do this entirely on codex?

[hi @nerdorgeek]

Pretty much work with chatgpt (not work/codex) to turn each next step in codex into a detailed prompt, then give that prompt to Codex (5.6 Ultra @ standard speed) to build it. I review what Codex outputs, bring the results back into ChatGPT, refine the next prompt, and repeat that loop until it’s done basically.
More detail and better ideas than if I had to use voice too.

[hi @nerdorgeek]

@AiEvolutio58513 this me 😭

[hi @nerdorgeek]

@tekbog I can’t wait for the day where mobile data is as fast as coax/fiber everywhere, I can see every letter & word in the other language be translated realtime, and get a pinyin-like experience when trying to respond in said persons language.

No idea the physical form, but I’m ready!