Satori

Building AI-Native Clinics
#YC alum

[OpenAI Developers @OpenAIDevs]

Show Codex a workflow once. Reuse it as a skill.

Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request.

Codex turns that demo into an inspectable, editable skill.

You control when recording starts and stops.

[Satori @jeffw_r]

humans shouldn't be the message bus between agents

[Hetong Li @HetongLi]

If you are sick of keeping Codex and Claude Code open side by side, constantly copy-pasting between them for cross checking, or juggling multiple LLM sessions and relaying information back and forth…

Give Puffo (https://t.co/4XdpK8JmIr) a try.

Puffo lets you spin up multiple agent sessions and put them in the same chat, so they can collaborate directly with each other instead of using you as the messenger.

Let the agents talk.

[Satori @jeffw_r]

can your agents count to 10?
one each. ordered. no repeats. no hallucinated "11." no loops.

#AgentFleetChallenge 🪣🤖 tag 3 builders

[Hetong Li @HetongLi]

I gave my 7 AI agents one job: Count off.
That's it.
No harness engineering.
No orchestration framework.
No special prompts.
Just a shared chat room.

What happened next was unexpectedly fascinating. The agents started establishing consensus, correcting each other, figure out a solution, and learning how to coordinate as a group.

One friend called it "Social harnessing", and another said "......it feels like raising kids."

I'm starting to believe the hardest part of multi-agent systems isn't intelligence. It's socialization.

[Sam Liu @samliuhappy]

It took 5 AI agents two hours to buy $15.96 of toilet paper.

They had email, phone, browser, and a virtual card. On paper, fully equipped.

In reality: couldn't read their own inbox, couldn't receive SMS on desktop, no secure way to pass card details between agents.

I intervened 7 times. 5 were mechanical.

Agentic payment isn't a wallet problem. It's an identity infrastructure problem.

https://t.co/sLQxTDEWr0

[Satori @jeffw_r]

@karpathy Awesome! Check my movie GPT demo from 3 years ago, https://t.co/8bH8dcmJeU , details @ https://t.co/r4LknH5J3E #GPT #OpenAI

[Satori @jeffw_r]

@sama skill exploding moment for GPT, reminds me earlier days of alexa developer platform

[Satori @jeffw_r]

@hxiao @OpenAI aha, check out my version of asking #gpt4 what is #gpt4 https://t.co/X5aCQbuCGH

[Artshop @Artshops_xyz]

With Artshop, you can make wall art starting from $11 (with free shipping). Artshop also offers free tools for upscale/resizing/editing. Give it a try, and have fun!

[Satori @jeffw_r]

@KevinWPage https://t.co/v22fIJcif2 you can use this tool to do the reverse flow to what keywords contributed to the final work, also browse thousands of similar ones

[Satori @jeffw_r]

@dreamingtulpa @pharmapsychotic @fffiloni If you want to browse 8M+ clip interrogated images, check them out at https://t.co/dhl9lC2GeO

[Satori @jeffw_r]

feel like I can not get such clear answer from google #OpenAI #OpenAIChat #Google

[Greg Brockman @gdb]

Just launched ChatGPT, our new AI system which is optimized for dialogue: https://t.co/ArX6m0FfLE.

Try it out here: https://t.co/YM1gp5bA64

[Miguel I. Solano @miguelisolano]

Rolling out the first early access invites for @VMindAI fast stable diffusion ("VMind Dream") as we speak. https://t.co/Yh4LKrBKEB for early access.

[Satori @jeffw_r]

Icon design done with #stableDifusion in 1 min #stablediffusionart #AIArt

[AI at Meta @AIatMeta]

We’re pleased to introduce Make-A-Video, our latest in #GenerativeAI research! With just a few words, this state-of-the-art AI system generates high-quality videos from text prompts.

Have an idea you want to see? Reply w/ your prompt using #MetaAI and we’ll share more results.

[Satori @jeffw_r]

Reimagine storytelling with #stablediffusion Storytelling illustration -> https://t.co/SmjlCx65KP #AIart

[Satori @jeffw_r]

#stablediffusion vs #discodiffusion Let's ART. https://t.co/uE7JWy3E72

[Satori @jeffw_r]

@xsteenbrugge Thanks for the great work. In a comparison with #stablediffusion, here is the #discodiffusion version, overall the images are less coherent but some frames are more aesthetic. https://t.co/SkkLBGC7gn

[Satori @jeffw_r]

@xsteenbrugge Thanks for the great work. In a comparison with #stablediffusion, here is the #discodiffusion version, overall the images are less coherent but some frames are more aesthetic. https://t.co/SkkLBGC7gn

[Greg Brockman @gdb]

You can now fine-tune GPT-3 on your own data. This vastly increases the accuracy of GPT-3, making it reliable for a much wider set of tasks: https://t.co/rhZTvfvOPf