Kostas Hatalis 🚀🪐

Founder/CEO @GocharlieAI | ECE Ph.D. @LehighU | Reviewer @IEEEorg | I build LLM Agents 🤖

[Kostas Hatalis 🚀🪐 @kostashatalis]

excited to share our latest early draft:

"Review of Case-Based Reasoning for LLM Agents: Theoretical Foundations, Architectural Components, and Cognitive Integration"

...edited in part using our own language model, Charlie!

What if LLM agents could reflect on THEIR OWN past experiences and adapt dynamically to new goals?

📄 Read the full paper here: https://t.co/ArUnz0CWAb

[Jay Sensei👾 @hckinz]

Google just released https://t.co/C2lgMD3hcQ🙌 it's like lovable+cursor+replit+bolt+windsurf all in one @testingcatalog

[Kostas Hatalis 🚀🪐 @kostashatalis]

With the US and China battling for #AI dominance, the EU looks to fall behind, especially with rumors of Mistral AI struggling before its IPO. 🤖

Having tried to raise from EU VCs in the past, I'll just say they don't value innovation as much as investors in the US. 🚀

As a dual citizen, I hope this will change!

[Kostas Hatalis 🚀🪐 @kostashatalis]

Check out my latest article: Significance of Procedural, Semantic, and Episodic Memory for LLM Agents https://t.co/lQ0sfgsRcS via @LinkedIn

[Kostas Hatalis 🚀🪐 @kostashatalis]

@alexiskold DM'd you on our full stack gen AI solution for businesses powered by our latest micro models!

[Kostas Hatalis 🚀🪐 @kostashatalis]

@Heshanka_ Congrats on the launch! MidFunnel sounds like a game-changer for making follow-ups easier👏 Looking forward to seeing it in action!

[Kostas Hatalis 🚀🪐 @kostashatalis]

I'm incredibly excited to announce Charlie 1! Our new LLM from @GocharlieAI offering:
🔹Versatility: Chat & Instruct
🔹Uncensored request responses
🔹Tuned for Developing: Easily integrates with RAG & System Instructions setup 📷

https://t.co/8QUVihZZqt

[Kostas Hatalis 🚀🪐 @kostashatalis]

Everyone talking about how @OpenAI solved Q*, but here at @GocharlieAI we're more interested in π*(a|s) 😎

[simp 4 satoshi @iamgingertrash]

With Q*, OpenAI have likely solved planning/agentic behavior for small models

Scale this up to a very large model and you can start planning for increasingly abstract goals

It is a fundamental breakthrough that is the crux of agentic behavior

[Kostas Hatalis 🚀🪐 @kostashatalis]

Q* is a well-known concept in RL. It signifies the optimal action-value function (ie you've learned the perfect action for a certain state to maximize value) for a certain environment. From an outside perspective, it sounds like a cool fancy term, definitely something an AI journalist could have picked up to go viral. But in the context of LLMs it is a bit meaningless unless you clearly define an environment with a set of actions and states. What is the context of Q* for this announcement?

[Kostas Hatalis 🚀🪐 @kostashatalis]

📢 The GoCharlie team is adding another to the pack!

🎉 I am super excited to announce the addition of Dustin Dannenhaur to accelerate our vision of building meta-cognitive agents, or more easily understood, self-improving AI Employees.

📊 Dustin has spent much of his professional career being one of the foremost researchers in metacognition for AI agents. Adding his expertise to our already stellar two-person AI team and our existing AI Agent offering makes us the most formidable AI agent-building team in the space.

[Kostas Hatalis 🚀🪐 @kostashatalis]

Hey everyone, https://t.co/gKjLemZG4U is throwing an AI Party!! 🎉

✨ I'm pumped for our team to host the AI Party on September 6th. We’ll cover our new agent product release, how @nvidia and @SRI_Intl see the rise of Multimodal AI, and how @hawkemedia sees AI's role in marketing.

Sign up here: https://t.co/hELUhVAUxD

Hope to see some of you there!

#theaiparty #gocharliego #generativeai #mutimodal #agents

[Kostas Hatalis 🚀🪐 @kostashatalis]

@ChrisGPotts Spot on

[Kostas Hatalis 🚀🪐 @kostashatalis]

We are seeing the rise of dozens of AI startups and labs raising $100Ms pre-product and pre-revenue whose teams are all ex-Google, Meta, Microsoft, and OpenAI.

The reality of the Matrix is that there is no such thing anymore as true entrepreneurship or objective scientific research.

There are only megacorporations passing around their tech and employees to each other to all profit. Outside startups and scientists be damned.

I hope smaller humble AI startups and scientists will prove this wrong!

#xai #openai #inflectionai #anthropic #cohere #adept #deepmind #aistartups

[Kostas Hatalis 🚀🪐 @kostashatalis]

A fantastic guide to Autonomous Agents! They are coming, and they WILL start augmenting or even automating whole workflows. 🤖

Everyone is having their minds blown away by generative AI models this year, but the world hasn't even seen the tip of the iceberg of what AI is capable of. 🚀

Get ready to embrace a future where autonomous agents become integral to our daily lives 💫

#intelligentagents #autonomousagents #GenerativeAI

[Matt Schlicht @MattPRD]

🤖📈 Autonomous Agents Are The Fastest Growing Open-Source Technology In History

- But... what are autonomous agents?
- How do they work?
- How can you build or use one?

I wrote you the best overview on the planet.

Get ready for your mind to explode 🤯

https://t.co/YUrrlzGthO

[Kostas Hatalis 🚀🪐 @kostashatalis]

I'm extremely excited for https://t.co/wOFc4TXu5i to be mentioned in the latest AWS blog as we begin working closely with them in training our domain-specific LLM and Multimodal Models! 😄

👉 https://t.co/HfrEV9Ytjl

#GenAI #GenerativeAI #LLMs

[Kostas Hatalis 🚀🪐 @kostashatalis]

Big things in development between @GocharlieAI and @SRI_Intl! Check out my interview below!

https://t.co/9amWNIi7kV

[Kostas Hatalis 🚀🪐 @kostashatalis]

By @pmarca, it's finally making it mainstream that AI is more beneficial than dangerous 🤩. Like @ylecun, I've always believed that AI will not destroy the world 🌍 and that it will not only save it but usher in a renaissance of boosted productivity 📈, creativity 🎨, and entertainment 🎉.

#GenerativeAI #FutureOfWork #AIart #gocharliego

[Marc Andreessen 🇺🇸 @pmarca]

Why AI Will Save The World
By Marc Andreessen

The era of Artificial Intelligence is here, and boy are people freaking out.

Fortunately, I am here to bring the good news: AI will not destroy the world, and in fact may save it.
🧵

[Kostas Hatalis 🚀🪐 @kostashatalis]

@natanielruizg @GoogleAI Incredible work! Will @GoogleAI release the model weights for this?

[Kay @kaysorin]

Such a fun workshop with @GocharlieAI @BrennanWoodruff talking about AI-Driven Content Creation! Great crowd, lots of good questions, and delicious cookies 🍪 Thanks @Techweek_ and @werqwise #SFTechWeek #TechWeek

[Kostas Hatalis 🚀🪐 @kostashatalis]

Are any other AI founders enjoying the fast pace of AI news? I'm personally loving how fast things are moving 😍