Alvaro

Data enthusiast

[Alvaro @eztati]

Has Been a year of coding

[Alvaro @eztati]

@gdb 2026 will be the year of collective intelligence—where autonomous agents seamlessly collaborate, forming dynamic networks that amplify human creativity, solve complex global problems, and elevate our shared capabilities beyond individual or isolated agent performance.

[Alvaro @eztati]

@jaydanurwin @bindureddy Gemini 2.5 is a reasoning model, while 4.1 not. Wonder if performance will go higher with reasoning

[Alvaro @eztati]

@samuelcolvin @pydantic I chose Pydantic AI over other alternatives only because I feel this project will not disappear any day, like other projects I tested in the past.

[Alvaro @eztati]

@tenobrus This was the anwer from google Gemini 2 flash .🤔

[Alvaro @eztati]

Skynet looks very cool!

[Boston Dynamics @BostonDynamics]

Atlas is demonstrating reinforcement learning policies developed using a motion capture suit. This demonstration was developed in partnership with Boston Dynamics and @rai_inst.

[Alvaro @eztati]

I wish LLM chat services like ChatGPT defaulted to temporary chats with a quick 'Save' button. The number of temporary chats I start greatly exceeds those I'd actually revisit.

[Alvaro @eztati]

@MatthewBerman https://t.co/SjG3OaXGpB

[Alvaro @eztati]

Vibe coding game idea: A text-based multiplayer diplomacy thriller where you never know if you're negotiating with a human or an AI that remembers every word you've ever said. Can you outsmart AI on its home turf?
#vibecoding

[Alvaro @eztati]

Vibe coding game idea: A text-based multiplayer diplomacy thriller where you never know if you're negotiating with a human or an AI that remembers every word you've ever said. Can you outsmart AI on its home turf?
#vibecoding

[Karun Singh @karun1710]

We’re hiring a Research Engineer at @Arsenal ⚽️ to help accelerate our applied research efforts!

We’re building state-of-the-art models to understand football at scale, and a suite of ML-powered applications on top of them to drive tactical and strategic decisions.

[OHDSI @OHDSI]

Please join our Nov. 26 (11 am ET) community call for a session focused on the #OHDSI2024 Collaborator Showcase honorees. 5 posters or demos were selected as Global Symposium Best Community Contribution honorees, and we will learn about each!

➡️ https://t.co/uOYDMPiare

[william @wgussml]

🚀 excited to announce 𝚎𝚕𝚕 v0.0.15 and full support for versioned prompt engineering in Jupyter notebooks!

sick of @langchain?

here's what we added:

[Alvaro @eztati]

@wgussml @aidan_mclau @williamgeronco @OpenAI Doubt - OSI Layer 8

[Alvaro @eztati]

@paulgauthier Is not o1 mini better at coding than o1 preview?

[Alvaro @eztati]

@petergyang @ChatGPT Something like voice-GPTs so you can provide context, then you can iterate over time in ideas, updating the context if needed.

[Thomas Dohmke @ashtom]

We will let people off the waitlist for o1-preview daily. Were moving. Also, I’m going to listen to my staff and not share Universe announcements.

What I can say: The IDE of today will be revolutionized, the IDE of tomorrow will be born. I’m hyped. See you there :)

[Alvaro @eztati]

@OpenAIDevs Are the presented results consistent in other languages? Spanish, French, etc.?

[Alvaro @eztati]

@nicdunz I also saw also pizza-model-small

[Andrew Mayne @AndrewMayne]

I've had access to @OpenAI's o1 for several weeks. My advice on using it:

1. Don’t think of it like a traditional chat model. Frame o1 in your mind as a really smart friend you’re going to send a DM to solve a problem. She’ll answer back with a very well thought out explanation that walks you through the steps.

2. Write your prompt in notepad. Plan out what you want. Explain all the steps – provide even more detail than you’re used to.

3. Use o1-mini for tasks that don’t require as much world knowledge but following things through step-by-step.

4. o1 tends to give me the parts of the answer and the complete response while o1-mini will give me the steps.

5. In my anecdotal and highly subjective experience, when you make corrections or adjustments, use patience in explaining what you need changed. Models that reason respond well to reasoned responses.

[Joanne Jang @joannejang]

🍓 there's a lot of o1 hype on my feed, so i'm worried that it might be setting the wrong expectations

what o1 is: the first reasoning model that shines in really hard tasks, and it'll only get better. (i'm personally psyched about the model's potential & trajectory!)

what o1 isn't (yet!): a miracle model that does everything better than previous models. you might be disappointed if this is your expectation for today's launch – but we're working to get there!