Rodolfo Anibal

P.h.D in Applied Mathematics, UNICAMP. Data Scientist Sr at Globant 🇨🇱 . Lecturer at University of Chile and UDP. Interested in audio and machine learning.

[Martin Bel @__mbel__]

We reached #1 at the SWE-bench-Multimodal benchmark with the @Globant Code Fixer Agent.

Kudos to team that made it happen!
@german_milano, @__mbel__, @mperezjodal, @RodolfoAni72304
@GMilano @jlamasrios

[Germán Milano @german_milano]

1/8
Everyone's doing great work building agents for bug fixing. But I'm curious—does anyone have insights on which types of issues your agents are good at, and which ones pose the biggest challenges? 🧵

Cc: @__mbel__ @jlamasrios @RodolfoAni72304 @GMilano @mperezjodal

[Gaston Milano Millan @GMilano]

Pleasure to met the #AG2 @Chi_Wang_ @qingyun_wu team! 🤝 Exciting to discuss their vision, which aligns with our work at @Genexus & @Globant. Tomorrow, join us https://t.co/T7sQZAM8U0 as we share our experience with pyautogen in Code Fixer Agent #1 SWE-Bench-Lite. @mperezjodal & code fixer team will be live to answer your questions about the future of software maintenance.

[Marcelo Pérez @mperezjodal]

Thanks for having us!

[Germán Milano @german_milano]

During our talk today, someone asked us for advice on building an AI Agentic System such as Code Fixer.

Instead of saying 'this is what you should do,' we want to share what worked for us and the lessons we’ve learned (so far!). 🧵

[Microsoft AI Frontiers @ms_aifrontiers]

Happening now!

cc: @Globant @GMilano @mperezjodal @german_milano @RodolfoAni72304 @__mbel__ @jlamasrios

[Germán Milano @german_milano]

Gran logro del equipo de @Globant Code Fixer, posicionándose 🥇en un ranking open source internacional!

[Guibert Englebienne @guibert]

Exciting news! This week, Globant’s code-fixing agent achieved the #1 spot on the SWE-bench lite industry standard. Nearly 50% of reported bugs were autonomously fixed by our agent. 💻✨

In our commitment to advancing the field, we’ve published a white paper detailing our strategy. For a quick summary, check out José’s insightful thread!

#AI #Coding #Innovation #GlobantEntepriseAI #AiAgents

[José Lamas @jlamasrios]

They've just updated the leaderboard, now showing Code Fixer as the #1. https://t.co/vG3JDwc7Mk #swebench

[José Lamas @jlamasrios]

6. Full technical details are available in the November 2024 Code Fixer white paper. https://t.co/cvd2EprkTb

[Guibert Englebienne @guibert]

This is a major milestone in @Globant's journey of innovation: AI Agents are the future of software development.

During the software development life cycle, lots of time is spent debugging and fixing old code. Imagine if you could have an AI that could solve about half of the tickets, freeing up devs for more meaningful work.

We’ve developed a Code Fixer AI Agent, and its performance has matched the state-of-the-art models in the SWE-bench-lite benchmark.

https://t.co/2FRbnl0kXU

[Gabriel Simonet @gabrielsimonet]

Congratulations to the amazing teams of @Globant and @GeneXus involved in this incredible achievement!! Top, top, top! 🦾 Code Fixer AI Agent is built on top of our @Globant Enterprise AI Platform. https://t.co/gX094Rplsn

[Martin Migoya @migoya]

.@Globant’s Code Fixer AI Agent ranked #1 in the SWE-bench-lite! Let’s keep redefining what’s possible in software engineering applying AI and allowing teams to be more creative! Go Globant Enterprise AI! Let’s rock!
https://t.co/RIk102vKYx