Alex Reibman 🖇️ Profile picture
May 20 19 tweets 7 min read Read on X
Google and OpenAI are at war. Just days apart, both unveiled 2 insanely powerful multimodal AIs— Gemini 1.5 and GPT-4o.

Who has the best LLM? We threw an emergency hackathon to find out.

Here are the finalists from the @solarissociety ⚔️ GPT-4o vs. Gemini 1.5 Hackathon (🧵):

Image
Image
Image
1/ Elevator - 🏆 Best use of Gemini 1.5

Steve Jobs AI powered by Gemini 1.5-multimodal audio (no speech to text at all) that gives feedback on elevator pitches.

Extremely detailed breakdown—Even understands tone, passion, and conviction
@__shubhankar
2/ Generative UX

Interactive travel agent that connects user preferences with trip guides, bookings, photos, cost planners, and more

@_bprimal_
3/ OpenRabbit - 🏆 Best use of Computer Vision @roboflow

Open sourced Rabbit R1 with local hardware. It can:
- Create music with Suno
- Send emails
- Curate playlists
And more

A better R1 but built in 24 hours

@notionsmith @sachscode @rama41296
Image
4/ Synthify

Use GPT-4o and Gemini 1.5 to generate synthetic datasets for smaller machine learning tasks

Cheap dataset curation

@saurishhh
Image
5/ George - 🏆 Best use of GPT-4o

AI agent to negotiate with food vendors and suppliers on WhatsApp marketplaces

Saving restaurants hundreds of dollars per month sourcing cheaper, higher quality ingredients

@_AbdullahNauman @apostoliev @arjundabra @jadroy2 @taylorzhuAI
Image
6/ RoboDebate Battle 2024

GPT-4o and Gemini 1.5 debate in front of a live audience— but the audience doesn’t know who is who.

Audience votes on the winner

7/ Engineer-4o - 🏆 Best in Show

VS code extension agent to automatically track issues and solve codebase issues

Built with @pyautogen

@ishaandey_ @ElijahKurien
8/ Glowby Debates

Live debate between GPT-4o and Gemini 1.5

@jacobilin
9/ HotAgents

Desktop agent that takes screenshots and figures out what tools to call automatically. It can summarize text, write code, and more

All with one hot key

Powered by @wordware_ai

@crsamra @kevinydzhu @avery_chiu @ariaxhan
10/ Turbot

AI agent that combines user requests with GPS location to plan uniquely personalized tour experiences

@kellyhongsn @ten_lukasz
11/ Thought Partner

AI assistant that listens to your notes, creates a live editable transcript, and sends you an email summary

Image
12/ Halo AI

Better Siri voice assistant for managing todos and calendar events
13/ Robodog

Computer vision powered robot trained to identify objects

@sebheyneman

14/ Twitter Times

Turn your Twitter feed into a newspaper

Web scraper opens a browser, parses your feed, and turns it into a 1 pager.

@itzelleyy
15/ AI Yapper

AI voice clone that synchronizes with your personal information and becomes a synchronized clone of you

@markokraemer
Huge thanks @thomasschulzz @jacobshamberger @solarissociety + @AgentOpsAI @wordware_ai @logicrite @AnonPlatform @browserbasehq

+ judges @mickeyxfriedman @rajko_rad @rememberlenny @josephofiowa @pk_iv @kwindla @AustinPeirson @luishectorcha @jtvhk

More AI? Follow @AlexReibman
@pyautogen @ishaandey_ @ElijahKurien here’s the video
7/ Engineer-4o - 🏆 Best in Show
(Reposting because upload didn't work)

VS code extension agent to automatically track issues and solve codebase issues. Built with @pyautogen

@ishaandey_
@ElijahKurien

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Alex Reibman 🖇️

Alex Reibman 🖇️ Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @AlexReibman

May 13
Meta launched Llama 3 to show the world what’s possible with open source LLMs.

500+ AI engineers just spent 24 hours straight putting it to the test.

Here’s what we saw at the @AIatMeta x @cerebral_valley #Llama3Hackathon (🧵):
Image
Image
1/ JoeCRM

AI-first CRM that receives signals about customers, performs research about them, and automatically drafts outreach campaigns

@GregTanaka
2/ Activation Ablation Augmentation

Research team that identified how to nullify activation layers in Llama3 responsible for censorship

@song_minjune @IanSears96 @Nottlespike

🥉 3rd place
Image
Read 12 tweets
Apr 23
We challenged 250+ hackers to build Agent Apps with AgentOps. The goal: Make an agent-powered startup in a weekend.

AI agents are coming to replace you.

Here are the finalists from the Cognitive Agents Hackathon by @AgentOpsAI x @MindsDB x @MayfieldFund (🧵):

Image
Image
Image
1/ Nexus AI

AI voice agent that calls vendors, fights for the best price, and negotiates with other vendors

AI agents for automating procurement officers w/ monitoring by @agentopsai

🥇First Place $1500 + Monitor

@wukevinl @sunnybak_ @narusevic @stateof_kate
Image
2/ AI Sales Outreach Crew

Automating an entire sales team with AI agents that research customers, find their contact info, and set up planned meetings

Built with @crewAIInc + @agentopsai cost tracking

🥈 2nd place $500 + Monitor + AirTags

@Bayka
Image
Read 9 tweets
Apr 12
Never underestimate the open source AI community.

These cracked engineers are here to break the limits of what’s possible with local LLMs. We just witnessed some nutty inventions.

Here’s what we saw at the @ollama Open Source and Local AI meetup at @cerebral_valley (🧵):
Image
Image
1/ Ollama: Concurrency mode

Run multiple local LLMs on one machine at the same time with shared resources

Even works with different models.
@ollama @dhiltgen
Image
2/ Bootleg Amazon Kindle

Running local LLMs and StableDiffusion on Raspberry Pi to create generative ebooks

Swap out parts for faster performance

Image
Image
Read 8 tweets
Mar 26
We invited 200+ engineers to take an exclusive look at the latest advancements in AI agent ecosystem

If you’re not following this space, your job is probably going to be replaced by AI.

Here’s what we saw at the @AgentOpsAI x @Relplicate Agent Meetup (🧵):
Image
Image
1/ AgentOps

Agents are slow, expensive, and unreliable. AgentOps is fixing that.

Track, test, and benchmark AI agents from prototype to production

@AlexReibman @AgentOpsAI @AtomSilverman @siyangqiu
2/ Reworkd

AI agents for navigating the web and scraping data

Introducing: Tarsier— an open source framework that combines web scraping and OCR to extract text from web pages for the consumption of LLMs

@asimdotshrestha @khoomeik @ReworkdAI
Image
Read 11 tweets
Mar 25
Mistral AI is what OpenAI would be if it were actually open.

And they just threw the largest OSS LLM hackathon to date. Over 2000 hackers applied to compete for $10k in prizes.

Here’s what we saw at the @MistralAI x @cerebral_valley hackathon (🧵):
Image
Image
1/ Prompt Parfait

Generative prompt creator that continuously improves

“Learning” by prompting, calculating the loss against evals, and updating the prompt

🥇1st place API track
Image
2/ Ambrozia

AI salespeople that answers questions about your business’s knowledge base with realistic generative voice and video

@eliotthoff @EmileCohen4
Image
Read 11 tweets
Mar 18
Llama Lounge just hosted the largest ever symposium of AI agent startups.

Over 400 VCs, builders, and innovators RSVP’d to get an exclusive look at the latest advancements in the SF AI startup scene.

Here’s what we saw at the Agents Llama Lounge by @BlitzVentures @jowyang (🧵):

Image
Image
Image
1/ AgentOps

Track, monitor, and benchmark AI agents. Test your agents against 1000+ benchmarks and monitor performance from prototype to production

Agent tracking, benchmarking, and compliance



@atomsilverman @siyangqiu @agentopsai

p.c. @Scobleizer github.com/AgentOps-AI/ag…

Image
2/ Commit

Agent that automatically writes job applications for you

It ranks open jobs, matches your skills against the roles, and submits your info automatically

@gunnr Agent.commit.dev

Image
Read 9 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(