Saurabh Singh
101 posts
@saurasingh
Research Scientist @ Poetiq, Ex-Google DeepMind, Opinions are my own.
We finally had a moment to run our system with GPT-5.2 X-High on ARC-AGI-2! Using the same Poetiq harness as before, we saw results as high as 75% at under $8 / problem using GPT-5.2 X-High on the full PUBLIC-EVAL dataset. This beats the previous SOTA by ~15 percentage points.
How do they produce such crazy papers?
We’re thrilled to announce a new chapter for Poetiq: We have closed $45.8M in Seed funding. It’s a privilege to build alongside partners who understand the scale of our vision, including Surface, FYRFLY, @ycombinator, 468, Operator Collective, NeuronVC, and HICO.
Poetiq has officially shattered the ARC-AGI-2 SOTA 🚀 @arcprize has officially verified our results: - 54% Accuracy – first to break the 50% barrier! - $30.57 / problem – less than half the cost of the previous best! We are now #1 on the leaderboard for ARC-AGI-2!
Poetiq has officially shattered the ARC-AGI-2 SOTA 🚀 @arcprize has officially verified our results: - 54% Accuracy – first to break the 50% barrier! - $30.57 / problem – less than half the cost of the previous best! We are now #1 on the leaderboard for ARC-AGI-2!
From another leading attempt at ARC-AGI. poetiq.ai/posts/arcagi_a…
Poetiq has officially shattered the ARC-AGI-2 SOTA 🚀 @arcprize has officially verified our results: - 54% Accuracy – first to break the 50% barrier! - $30.57 / problem – less than half the cost of the previous best! We are now #1 on the leaderboard for ARC-AGI-2!
Poetiq has officially shattered the ARC-AGI-2 SOTA 🚀 @arcprize has officially verified our results: - 54% Accuracy – first to break the 50% barrier! - $30.57 / problem – less than half the cost of the previous best! We are now #1 on the leaderboard for ARC-AGI-2!
ARC-AGI was supposed to be LLM-proof and show that LLMs are not the way to AGI. LLMs are crushing it. 🔥
Fukushima's video (1986) shows a CNN that recognises handwritten digits [3], three years before LeCun's video (1989). CNN timeline taken from [5]: ★ 1969: Kunihiko Fukushima published rectified linear units or ReLUs [1] which are now extensively used in CNNs. ★ 1979: Fukushima published the basic CNN architecture with convolution layers and downsampling layers [2]. He called it neocognitron. It was trained by unsupervised learning rules. Compute was 100 times more expensive than in 1989, and a billion times more expensive than today. ★ 1986: Fukushima's video on recognising hand-written digits [3]. ★ 1988: Wei Zhang et al had the first "modern" 2-dimensional CNN trained by backpropagation, and also applied it to character recognition [4]. Compute was about 10 million times more expensive than today. ★ 1989-: later work by others [5]. REFERENCES (more in [5]) [1] K. Fukushima (1969). Visual feature extraction by a multilayered network of analog threshold elements. IEEE Transactions on Systems Science and Cybernetics. 5 (4): 322-333. This work introduced rectified linear units or ReLUs, now widely used in CNNs and other neural nets. [2] K. Fukushima (1979). Neural network model for a mechanism of pattern recognition unaffected by shift in position—Neocognitron. Trans. IECE, vol. J62-A, no. 10, pp. 658-665, 1979. The first deep convolutional neural network architecture, with alternating convolutional layers and downsampling layers. In Japanese. English version: 1980. [3] Movie produced by K. Fukushima, S. Miyake and T. Ito (NHK Science and Technical Research Laboratories), in 1986. YouTube: youtube.com/watch?v=oVYCjL… [4] W. Zhang, J. Tanida, K. Itoh, Y. Ichioka. Shift-invariant pattern recognition neural network and its optical architecture. Proc. Annual Conference of the Japan Society of Applied Physics, 1988. First "modern" backpropagation-trained 2-dimensional CNN, applied to character recognition. [5] J. Schmidhuber (AI Blog, 2025). Who invented convolutional neural networks? x.com/SchmidhuberAI/…
Poetiq has officially shattered the ARC-AGI-2 SOTA 🚀 @arcprize has officially verified our results: - 54% Accuracy – first to break the 50% barrier! - $30.57 / problem – less than half the cost of the previous best! We are now #1 on the leaderboard for ARC-AGI-2!
