Jay Scambler
@JayScambler
Followers
4,832
Following
783
Media
155
Statuses
1,025
Techno optimist. Applied AI Engineering @GreyHavenAI . Finding Ikigai.
Oklahoma City, OK
Joined May 2019
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
#خلصوا_صفقات_الهلال1
• 838697 Tweets
ラピュタ
• 408751 Tweets
Atatürk
• 391804 Tweets
Megan
• 225825 Tweets
Johnny
• 225103 Tweets
Sancho
• 150235 Tweets
MEGTAN IS COMING
• 133896 Tweets
#4MINUTES_EP6
• 128070 Tweets
RM IS COMING
• 127281 Tweets
namjoon
• 120999 Tweets
olivia
• 118822 Tweets
Coco
• 53451 Tweets
Labor Day
• 50588 Tweets
كاس العالم
• 47821 Tweets
ミクさん
• 46553 Tweets
ムスカ大佐
• 41106 Tweets
#フロイニ
• 37547 Tweets
Arteta
• 35129 Tweets
ŹOOĻ記念日
• 24633 Tweets
ミクちゃん
• 22995 Tweets
Javier Acosta
• 22436 Tweets
Día Internacional
• 21751 Tweets
Romney
• 18098 Tweets
Ramírez
• 16983 Tweets
Lolla
• 14892 Tweets
ナウシカ
• 13796 Tweets
Lo Celso
• 12045 Tweets
Sekou Kone
• 11059 Tweets
AFFAIR EP1
• 10504 Tweets
نادي سعودي
• 10392 Tweets
The pace of development surrounding Baby AGI and AutoGPT is mind blowing. Seems like a new *groundbreaking* update comes out every hour
Here are a few examples just from the past 24 hours
105
761
5K
Groq is serving the fastest responses I've ever seen. We're talking almost 500 T/s!
I did some research on how they're able to do it. Turns out they developed their own hardware that utilize LPUs instead of GPUs. Here's the skinny:
Groq created a novel processing unit known as
66
239
1K
AutoGPT and BabyAGI are yesterday’s news. Want to see what happens when AI agents have a conversation with each other?
Here are a couple examples of CAMEL!
35
136
996
AutoGPT directly in your browser if you just want to test out some of its functionality! Really cool to get a sense of what all the hype is about
6
65
665
LangChain for Baby AGI. This could be huge over the next few days! Keep an eye out
Baby-AGI by
@yoheinakajima
is taking the world by storm
Here's an implementation within the
@LangChainAI
framework, allowing you to easily substitute in other vectorstores and other LLMs
Docs:
55
308
2K
3
20
342
@TheLeanAcademic
In very simplified terms they are able to tell themselves what to do next without prompting from the user
10
10
326
I launched a website today that helps people find gigs in the Web3 economy. My goal is to better connect our communities and support the future of work. Help me spread the word with a RT and a like!
14
65
173
Baby AGI that’s super close to developing executable actions on its own!
I created BabyAGI-asi, a modification of
@yoheinakajima
's babyagi that runs arbitrary python code to perform tasks - It manages to create routines for pyautogui, webscrapping, manages to execute actions on the computer and even controls its own memory🧵
21
90
521
2
8
156
@London_Lady
I think fear of the unknown is initially a natural response. This technology will result in upheaval of our current societal norms over time. It is inevitable. Recursive agents are a big breakthrough in the application of the tech and will be incredibly powerful in time. We may
18
11
138
I’ve been thinking a lot recently about the future of verifiable credentials and felt like I needed to get some thoughts down on the page
I’m not a thread guy, but I know many appreciate tl;drs. Here is a snippet of main points I cover 🧵 (1/14)
6
24
138
AutoGPT, BabyAGI, and CAMEL have ushered in a new form of AI technology and we need a way to classify them.
I’ve been talking with other builders and workshopping names. Best one so far: Collaborative Agent Modules aka CAMs
Have a suggestion? Share it in the comments!
28
23
117
Another version written in Typescript
Ok, the time is right to open source this: introducing GPT-Legion, an autonomous agent framework:
Similar in spirit to AutoGPT and Baby AGI, but written in the superior language that is TypeScript!
33
105
738
3
4
113
The creator of CAMEL showing off the initial concept.
1
14
113
Recursive agents with access to your your company’s apps and shared data.
@thegarrettscott
executes and delivers in record time once again
Over the weekend I finished the to-do list that does itself.
Everytime you add a task, a GPT-4 agent is spawned to complete it. It already has the context it needs on you and your company, and has access to your apps.
It’s called the Do Anything Machine (Link in thread)
134
321
3K
2
6
94
The Extropic litepaper just dropped!
It contains some long awaited info about what they're building and how it will enhance compute for AI. Here are some key details:
The demand for computing power in AI is growing exponentially, but traditional digital processors are hitting
4
6
64
Chat between an “AI founder” agent and an “AI VC” agent. Interesting to see the power dynamic between the agents
Built "Startup Simulacra" using
@LangChainAI
and
@guohao_li
's CAMEL architecture.
A VC Agent evaluates a Founder Agent's randomized startup idea: "Personalized cereal boxes to celebrate child's achievements"
Super interesting how an adversarial agent drives reasoning!
11
30
152
4
5
64
@ektepenger
Almost. People are definitely experimenting around similar use cases
Had AutoGPT make me a more complicated website, from scratch this time:
it:
- created login/sign up page
- styled it with bootstrap
- created flask api for login / logout
- created a local json database
Took ~10 minutes at a cost of $0.50. More examples coming
29
79
775
1
0
54
@AdamRackis
Guiding ai to good results might become the only real job for knowledge workers in most domains
4
2
50
Replit template that allows you to play around with the prompts for yourself! Just need an API key
ChatGPT agents interacting with each other? Let's see it in action! 🤖💬
Here's the
@LangChainAI
implementation of CAMEL: Communicative Agents for “Mind” Exploration of LLM Society 🐪
Fork this template on
@Replit
to get started:
5
55
241
1
1
48
@AminMemon
Keep posting into the ether. People are listening even when you don' think they are. The more knowledge you share the more you'll be rewarded.
2
0
49
Check out how fast the response time is for yourself here
4
0
46
NFTs represent what you own
Verifiable Credentials represent who you are
3
10
40
@hey_rushik
I initially felt the same way, but you can’t look at it like that. Knowledge is the culmination understanding. Each new development of this tech helps to broaden that understanding of how it can be applied. You just have to remain curious enough to keep exploring!
1
2
39
@varun_mathur
@JeffBezos
@sama
@satyanadella
@sundarpichai
@elonmusk
@ylecun
@finkd
@GroqInc
$8 trillion goes a long way. Could probably have this deal inked in the next 24 hours
2
0
37
@AshmeadeBanks
@TheLeanAcademic
Options are pretty limited.
@yoheinakajima
published a version of BabyAGI in Replit which is fairly easy to use. This is also a nice interface to test out for BabyAGI
Amazing work by
@dory111111
with
@yoheinakajima
's BabyAGI using
@streamlit
and
@LangChainAI
web app. I modified it to select GPT models, adjust temperature, also made it so folks who aren't familiar with Poetry can run it directly using Python.
Repo 👇
11
46
382
1
3
36
If you were 100% reliant on OpenAI you need to start exploring open source models TODAY – These are some of my favorite resources and applications. Links below. Who else am I missing?
1.
@LMStudioAI
2.
@Ollama_ai
3.
@NousResearch
4.
@shoggothsystems
5.
@HarperSCarroll
6
4
37
Group chat between agents. Could see this being a cool way to experiment with a “board of advisors” style agents
Behold GroupChatGPT 👨👩👧👦, take ChatGPT from awkward 1:1 conversation into a lively group chat with your favorite characters.
Rick Sanchez, Barbie, Cartman, and Yoda going at it about the meaning of life.
Try it out here:
20
33
240
2
1
35
Are you happy? How do you define happiness? I've been pondering these questions and how they intersect with the future of Web3
Again... not a thread guy, but I realize people have short attention spans. Here are a few of the main points I cover 🧵(1/14)
3
6
32
Why aren’t recursive AI agents like AutoGPT and BabyAGI useful yet?
One of the biggest limiting factors has been their inability to retain memories and learn from them.
Here are a few examples of builders solving this problem!
7
4
34
Web3 doesn’t actually fix anything until we start recognizing people because of their merits instead of their money
1
4
30
Verifiable credentials are going to be a much better way to manage token gated access than NFTs
3
3
28
Everyone is holding back on announcements today because they don't want to get overshadowed by GPT-5 — wonder how long this holding pattern will last?
3
1
27
@OpenAI
Feel like we all need a personal injury attorney for how much whiplash you’re giving us
0
0
24
1
1
22
@bcrussett
@mattshumer_
Seems to be available. Only caveat I can find is that they are generally compatible with ML frameworks such as PyTorch and Tensorflow for inference, but don't support training.
2
1
21
@levelsio
They developed their own hardware that are built using LPUs instead of GPUs!
Groq is serving the fastest responses I've ever seen. We're talking almost 500 T/s!
I did some research on how they're able to do it. Turns out they developed their own hardware that utilize LPUs instead of GPUs. Here's the skinny:
Groq created a novel processing unit known as
66
239
1K
0
2
21
We live in a Brave New World
My next demo using
@GroqInc
: writing a novel in two minutes.
Behind the scenes, there's tons of reasoning and rewriting going on. This only shows the surface-level results.
More than 25K tokens are generated here, in less than two minutes.
On-demand books are now a reality!
36
47
397
3
1
20
@neb301
@London_Lady
I’m not assuming that all technological progress is beneficial. I’d argue the application of any technology is what makes it beneficial. The creation of stone and various metal tools allowed us to advance our civilizations, but they also made waging war much more efficient.
3
1
19
Run LLMs locally and serve them as an API for your projects
2
1
18
Bookmark these tweets! Will update as more use cases are released.
1
0
18
The recommendation to advance DIDs by the
@w3c
seems trivial to most of us, but is actually a major step forward in our fight for digital privacy and sovereignty!
Our institutions have failed us
@timberners_lee
just gave us tools to protect our rights
0
1
17
@rsg
@TurnerNovak
@balajis
A circle would make more sense in practice. If one section of the Line were compromised it would make public transit pretty useless
3
0
16
I have extreme FOMO watching the Devin demos — can anyone help me get off the waitlist?
5
0
16
How we interact with AI is about to change thanks to AutoGPT and BabyAGI.
Interfaces like Graphologue will allow us to easily manage multiple agents at a time. Is this the next Chatbot UI?
Stop reading the text !!! Have a graphic dialogue with OpenAI’s
#GPT4
with
#Graphologue
. It turns GPT4-generated text into interactive node-link diagrams in real-time. New Human-Computer Interaction
#HCI
research makes
#AI
easier to use. More at
63
242
1K
1
2
14
This might *actually* be a game changer for the application layer
1
0
15
Product releases don’t matter if they are followed by this
1
2
13
So I’ve been drinking Fresca for as long as I can remember. I have memories sipping it in my bubble bath as a kid. I love the stuff. However, in an effort to be healthy, I gave up soft drinks in high school. I just looked on the back and realized it has 0 calories and no sugar...
1
0
14
After seeing the login with OpenAI demo put together by Genesis I dove into the docs for Passes (the auth framework that made it possible)
Here are some key takeaways and why I think it’s awesome especially for inter-app communication within AI
At its core, Passes enables
1
3
14
Complaining that AutoGPTs haven’t done anything useful is like saying the Wright Brothers’ airplane was a novelty. What we build today is only the first flight.
1
2
14
ChatGPT has revived my love of cooking!
Every recipe I’ve tried has been out of this world good! My friends and family can’t stop raving about them. Here are a few of my favorite prompts to generate secret recipes!
3
3
13
Forkable AutoGPT repl for those that prefer to use Replit (A little more accessible than running locally)
2
2
12
I know they say imitation is the highest form of flattery…
but did you really have to rip my tweet word for word?
@heyBarsee
3
0
12
Is it a common phenomenon to crave and order ginger ale on plane rides or is is just me?
0
0
12
There’s a future where credentials keep government officials accountable
Facts are no longer alternative if they’re verifiable
We could be an informed electorate once again 🗽
2
0
13
More insight on the implications of Q* / QUALIA – Using mathematical logic beyond our comprehension to break encryption AND suggest changes to itself
So this is what caused the open ai board to freak out.
The found a new model that could lead to AGI
One that used new maths to break encryption that would’ve taken 37 years to crack.
YT link below
65
211
1K
8
6
8
There’s no better feeling than finishing off two helpings of Christmas dinner and a few slices of pie, leaning back to enjoy your accomplishment, and breaking your sister-in-laws new Wayfair bench in the process
0
0
11
The more I talk with people about the power of verifiable credentials the more I am convinced they are the future of Web3
They are the true unlock of freedom and sovereignty in the internet
1
2
12
@wagieeacc
Hyperspace is thinking the same thing
We pushed out a release to reduce dependency on HuggingFace custom logic for downloading models given the significant outage they experienced some days ago.
Simply making the aiOS™ more robust for the future 💪
#DecentralizedAI
7
4
70
0
1
12
Pervasive question on my mind as we move towards AGI — are we trying to create a god or is God manifesting itself through creation?
4
1
12
@ponzzicapital
I haven’t specifically for Baby AGI or AutoGPT, however I could see a use case for creating more interesting scripts
0
0
11
Huge business opportunity here for college campuses — create a super simple no hassle interface using fine tunes of the lectures and coursework
3
0
11
Nous Research is my favorite team to follow. Join their Discord to see what I mean. Also check out
@Teknium1
for incredible insights into their models.
1
1
10
@dabit3
So far so good! On the agency side the hardest part has been finding the right clients with a large enough budget to spend, risk profile to explore, and lack of internal expertise to build.
1
0
10
@seanxthielen
Apple already has the hardware infrastructure to incorporate AI into every facet of our life. They just need to make a few tweaks and train a SOTA LLM
1
0
9
This would be a killer product, but requires better infrastructure and interoperability between RAG applications. Everything is too siloed currently. Who wants to help build the Plaid of RAG?
Please can somebody build this, my family is starving
57
14
431
3
1
10
Can't put my finger on it, but it feels like the wind has been taken out of OpenAI's sails recently
2
0
10
@GregKamradt
Have you checked out
@jxnlco
instructor for structured output? Really cool extraction for pydantic and zod data validation with LLMs
2
1
8
Is there anything better than hot ramen paired with an icy Sapporo on a cold night?
2
0
10
The trickle of information being generated, directed, and coordinated by OpenAI right now leads me think something is coming soon — usually they like to make sure everyone is speculating and generating buzz to precook the Twitter algo before a release
3
1
10
@jxnlco
Silicon Valley was prophetic. No need for a 7th season since they live in a post AGI world.
0
0
8
Now this is cool! A much needed lightweight way to bring your own API keys
0
1
9
Anyone remember how vocal Elon was about pausing AI last year? Sounds like a lot of double speak to me. In typical fashion if he doesn't have FULL control he throws a fit. He actually might be the biggest threat to open source and acceleration efforts. Time to open our eyes.
We are dedicated to the OpenAI mission and have pursued it every step of the way.
We’re sharing some facts about our relationship with Elon, and we intend to move to dismiss all of his claims.
2K
2K
13K
0
1
9
Starting a new company? Need help with a rebrand? Try this prompt with GPT-4 to work with a creative genius.
Prompt in Alt
0
0
9
I am a recent convert to Obsidian and now evangelize every opportunity I can. The community built plugins and support are amazing.
Love letter to
@obsdmd
to which I very happily switched to for my personal notes. My primary interest in Obsidian is not even for note taking specifically, it is that Obsidian is around the state of the art of a philosophy of software and what it could be.
- Your notes are
386
925
9K
1
1
8
How cool! Didn't realize my article was featured in the
@banklessDAO
newsletter. Thanks for the heads up
@psykoreactor
!
ScholarshipDAO by
@guptaastha00
Credential Economy by
@JayScambler
Good reads in the new
@banklessDAO
newsletter
0
0
1
4
0
9
@skirano
@yoheinakajima
@Replit
Awesome work! Forked the repl and added to my BabyAGI and AutoGPT thread for others to find. Thanks Pietro!
1
0
9
Autonomous Agents will completely change our relationship with AI!
Check out this demo to see how we can create Agents for repeatable tasks. AutoGPT integration coming soon!
2
1
8
The response time from groq feels like magic!
Wild tech you have to try:
They are serving Mixtral at nearly 500 tok/s.
Answers are pretty much instantaneous.
Opens up new use-cases, and completely changes the UX possibilities of existing ones.
73
168
2K
0
1
9
I started consulting as a fractional CFO for a couple SMBs last year and picked up enough clients to start a firm.
It’s incredibly rewarding being able to help so many different businesses!
Here are a few takeaways that every owner and operator can benefit from
🧵
1
5
9
brb going to take a private tour of the OpenAI Sora Museum of Fine Art real quick
1
2
9
Really cool extension of AutoGPT’s functionality! Now you can easily give the agent feedback and suggestions as it completes tasks. Great work
@_Lonis_
!
1
3
9
I highly respect what LangChain and Llama Index have done, but honestly they are more confusing and time consuming than just building your own custom pipeline once you know the providers you want to use
1
0
8