guille_bar Profile Banner
Guillermo Barbadillo Profile
Guillermo Barbadillo

@guille_bar

Followers
1K
Following
559
Media
58
Statuses
472

In a quest to understand intelligence Hablando de IA en español en la TERTULia: https://t.co/SCEoGWzBYd

Pamplona, Spain
Joined February 2018
Don't wanna be here? Send us removal request.
@guille_bar
Guillermo Barbadillo
2 years
Evolution of computing power over time
Tweet media one
1
1
18
@guille_bar
Guillermo Barbadillo
15 days
RT @OriolVinyalsML: Hello Gemini 2.5 Flash-Lite! So fast, it codes *each screen* on the fly (Neural OS concept 👇). The frontier isn't alw….
0
270
0
@guille_bar
Guillermo Barbadillo
20 days
RT @vitrupo: Anthropic co-founder Ben Mann says we'll know AI is transformative when it passes the "Economic Turing Test.". Give an AI agen….
0
89
0
@guille_bar
Guillermo Barbadillo
20 days
RT @matiass: Intento no antropomorfizar la IA, pero el otro día me hizo llorar
0
15
0
@guille_bar
Guillermo Barbadillo
23 days
ARC-AGI-3 will be interactive and similar in spirit to Animal-AI Olympics by Matthew Crosby.
@arcprize
ARC Prize
24 days
Interactive Reasoning Benchmarks are the next step in frontier evaluations. Hear @GregKamradt share why measuring human-like intelligence requires multi-turn environments. Including a sneak peak of ARC-AGI-3. Want to help us build interactive evaluations? We're hiring
1
2
27
@guille_bar
Guillermo Barbadillo
1 month
RT @Kyle_L_Wiggers: Google quietly released an app that lets you download and run AI models locally
0
4
0
@guille_bar
Guillermo Barbadillo
1 month
RT @MetaPuppet: This is Plastic. Made with Veo3. Spoilers in the next post. Watch before reading
0
537
0
@guille_bar
Guillermo Barbadillo
2 months
LLMs, RL, and rockets! 🚀 Cool paper showing how test-time reinforcement learning can optimize engineering problems when a continuous reward signal is available.
@tobyrsimonds
Toby Simonds
2 months
🚀 New paper: LLMs for Engineering: Teaching Models to Design High-Powered Rockets 🚀. We built an environment to allow models to build high powered rockets and show by using RL models can surpass human designs!
Tweet media one
Tweet media two
0
0
10
@guille_bar
Guillermo Barbadillo
2 months
This leaderboard visualization is updated daily:
0
1
14
@guille_bar
Guillermo Barbadillo
2 months
After a month of competition, no team is on track to reach the 85% needed to win the ARC Grand Prize through linear progress. New ideas are needed to drive breakthroughs and reach the grand prize this year. @arcprize
Tweet media one
11
35
228
@guille_bar
Guillermo Barbadillo
2 months
The released version of o3 scores just 3% on ARC-AGI-2. Adaptation to novelty is still an unsolved problem in AI (and intelligence is all about adaptation to novelty).
@arcprize
ARC Prize
2 months
o3 and o4-mini on ARC-AGI's Semi Private Evaluation. * o3-medium scores 53% on ARC-AGI-1.* o4-mini shows state-of-the-art efficiency.* ARC-AGI-2 remains virtually unsolved (<3%). Through analysis we highlight differences from o3-preview and other model behavior
Tweet media one
17
20
183
@guille_bar
Guillermo Barbadillo
2 months
RT @interconnectsai: OpenAI's o3: Over-optimization is back and weirder than ever.Tools, true rewards, and a new direction for language mod….
0
14
0
@guille_bar
Guillermo Barbadillo
3 months
RT @TheAhmadOsman: Microsoft just released the first natively trained 1-bit model: BitNet 2B. Trained on 4 Trillion tokens. Native 1.58-bi….
0
154
0
@guille_bar
Guillermo Barbadillo
3 months
Happy to be the first team to break the 10% barrier on ARC-AGI-2. I hope to make small improvements in the next days, but hitting 20%+ might take some black magic. 🧙‍♂️
Tweet media one
Tweet media two
@fchollet
François Chollet
3 months
When do you think we'll see the first >10% ARC Prize entry on Kaggle?.
40
38
473
@guille_bar
Guillermo Barbadillo
3 months
Gracias a gpt-4o ahora puedo dedicarme a mi verdadera vocación
Tweet media one
0
0
11
@guille_bar
Guillermo Barbadillo
3 months
RT @PJaccetturo: What if Studio Ghibli directed Lord of the Rings?. I spent $250 in Kling credits and 9 hours re-editing the Fellowship tra….
0
13K
0
@guille_bar
Guillermo Barbadillo
3 months
Time to try new ideas!.
@arcprize
ARC Prize
3 months
ARC Prize 2025 is Live. $1M competition to open source a solution to ARC-AGI. Your objective: Reach 85% on the private evaluation dataset. Progress needs new ideas, not just scale
Tweet media one
3
1
18
@guille_bar
Guillermo Barbadillo
3 months
It also modifies images of other objects, such as cars
Tweet media one
0
0
1
@guille_bar
Guillermo Barbadillo
3 months
Gpt-4o modifies the face of the person, even when being requested just to make the background transparent. Not sure if this is a failure of the model, or a "feature" to prevent editing images that preserve the identity.
Tweet media one
1
0
2
@guille_bar
Guillermo Barbadillo
3 months
RT @TheHumanoidHub: Unitree G1 stays on beast mode.
0
530
0
@guille_bar
Guillermo Barbadillo
3 months
Nice talk about "AI for Humanoid Robots" by @pabbeel on the GTC:
Tweet media one
0
0
0