Ricardo mahfoud

AI-First Software Engineer

[Ricardo mahfoud @RicardoMahfoud]

@levelsio There are plenty of third party apps out there with nice UIs that allow you to use any model with your own API key or with a subscription to that third party app.

No need to miss out on a better model because of UI. For example, as a SWE, I just use Cursor with both models.

[Ricardo mahfoud @RicardoMahfoud]

Cursor Tab vs Github Copilot - which one is the better autocomplete tool?

Watch this quick video to find out

[Lex Fridman @lexfridman]

I'm doing a podcast with the Cursor team. If you have questions / feature requests to discuss (including super-technical topics) let me know!

For those not familiar, Cursor is a code editor based on VSCode that adds a lot of powerful features for AI-assisted coding.

I've been using Cursor and love it, so I thought why not talk to the team. The founders are a bunch of brilliant folks from MIT.

This conversation will be bigger than just about Cursor, but more generally about the future of programming with AI.

[Ricardo mahfoud @RicardoMahfoud]

@aml_chandran As of today, Composer needs Pro subscription.
The other features don't and can be used with your own API key though (such as ⌘K or ⌘L)

I've been using API keys without pro for a long time, but Composer made it worth the Pro subscription IMO.

[Ricardo mahfoud @RicardoMahfoud]

Need a quick demo of the best Cursor features?

Watch my workflow where I create a native macOS app using Cursor Composer in under 8 minutes without writing a single line of code.

[Ricardo mahfoud @RicardoMahfoud]

🤯

[Matt Shumer @mattshumer_]

This is absolutely insane. A model is generating this game, in real-time, as the user plays.

Map the progress/trajectory of most other AI modalities onto this, and in a few years, we’ll have AAA-quality games being generated in real time.

[Jecelyn Yeen 🐟 @jecfish]

Spot the new lightbulb icon #ChromeDevTools? Click on it to see how #Gemini can help you with the error!

Try it yourself👇

[Shubham Saboo @Saboo_Shubham_]

OpenInterpreter with Llama-3 running locally on your computer (100% free and without internet):

[Alex Banks @thealexbanks]

Google just announced Med-Gemini for medical tasks.

It beats GPT-4 on all benchmarks:

[Matt Shumer @mattshumer_]

The dataset is everything.

Great read: https://t.co/snGcPx0M16

[Ricardo mahfoud @RicardoMahfoud]

Imagine an AI integration that executes as fast as normal code 🤯

[Matt Shumer @mattshumer_]

My mind is blown.

@GroqInc is serving LLaMA 3 at over 800 tokens per second!

800. Tokens. Per. Second.

This unlocks so many incredible use-cases.

It's one thing to see my demo — it's another thing entirely to experience it for yourself.

Do yourself a favor and try it asap.

[Ricardo mahfoud @RicardoMahfoud]

AI's 'No' isn't the end—just a nudge to dig deeper! 🕵️‍♂️ Found out GPT missed a Chrome API flag available since 2017. Always explore beyond AI's limits; its 'no' might just mean 'not yet' or 'not in my data.'

[Matt Shumer @mattshumer_]

We're entering a new world where GPT-4-level models are open-source and freely accessible.

Absolutely massive.

[Ricardo mahfoud @RicardoMahfoud]

New model available in Cursor! If you can't see it in settings, you can add it: "gpt-4-turbo-2024-04-09" 🚀

[Cursor @cursor_ai]

Cursor users can now use the new gpt-4-turbo model. We’ve observed improved reasoning on complex tasks.

Example comparison between gpt-4-1106 and the new gpt-4-turbo below:

[Ricardo mahfoud @RicardoMahfoud]

Exactly, you get the best of both worlds! Plus, it's super easy to switch models in cursor

[Pietro Schirano @skirano]

The biggest alpha in coding with AI right now is:

Debug with GPT-4, Code with Claude 3.

GPT-4 is still king when it comes to logic, but it's extremely lazy.
Meanwhile, Claude would do anything you ask.

The duo together is unbeatable.

[Ricardo mahfoud @RicardoMahfoud]

Exactly, Almost all my chatGPT responses include these! I use this custom GPT as a post-response filter to remove those useless buzzwords https://t.co/vguH6zSJ7A

Example: https://t.co/slyXoBF5y6

[SkalskiP @skalskip92]

detecting AI-generated text

researchers studied the impact of ChatGPT on AI conference peer reviews, confirming what we all knew

paper: https://t.co/Dlj7AEJI0h

↓ read more

[Aman Sanger @amanrsanger]

Long context models with massive custom prompts (~2M) may soon replace fine-tuning for new knowledge!

Let’s explore why:
(1/10)

[Min Choi @minchoi]

Education will never be the same.

People are finding some incredible use cases with Apple Vision Pro and spatial computing.

10 wild use cases:

1. Learning how heart works

[Jeff Dean @JeffDean]

We're starting to roll out API support for Gemini 1.5 Pro for developers. We're excited to see what you build with the 1M token context window!

We'll be onboarding people to the API slowly at first, and then we'll ramp it up. In the meantime, developers can try out Gemini 1.5 Pro in the AI Studio UI right now:

https://t.co/HG3inVgrc7