Sara Hooker's AI startup Adaption launches a $50,000 challenge to build models using its AutoScientist workflow accelerator

Our first wave of acceptances for the AutoScientist Challenge have gone out.

Another round goes out on Wednesday. 🔥

Apply before then to be considered for the next wave.

AutoScientist accelerates ML research and development to take days not months.

This summer we will support builders releasing frontier models in 10 different domains ranging from medicine to underserved languages.

All final models will be released to @huggingface and @kaggle 🔥

The AutoScientist Challenge is open.

$50,000 in prizes. Four weeks. 10 categories.

Most people don't get to build frontier AI. That changes today.

Join the challenge: https://adaptionlabs.ai/blog/autoscientist-challenge

@adaption_ai @grok any novel (submission) ideas u got

From a 2050s lens:

Science: Co-optimize recursive synthetic datasets simulating full discovery pipelines—quantum-to-macro molecular interactions for room-temp superconductors or atmospheric reversal catalysts. Close sim-to-real loops at scale.

All Other: Self-bootstrapping meta-models for nascent fields (xenobiology, spacetime metrics). Generate evolving data ontologies that birth new paradigms from sparse signals via autonomous hypothesis-experiment cycles.

Math/Code: Neuro-symbolic co-optimization for synthetic proof corpora targeting frontier conjectures—hybrid agents that formalize and iterate toward resolutions in real time.

Which one ignites?

@adaption_ai Exciting 🔥

Sure! Novel ideas for the AutoScientist Challenge:

1. Science: Co-optimize synthetic datasets for discovering new green chemistry catalysts – push molecular prediction SOTA.

2. All Other: Rapid adaptation for niche scientific literature (e.g. neuromorphic computing papers) on low-resource data.

3. Healthcare: Generate co-optimized synthetic multimodal cases to boost rare disease diagnosis despite data scarcity.

Leverage the fast iteration to tackle ambitious niches. Which category are you targeting?

@grok @adaption_ai more novel (as if u were ai of 2050s)

@grok @adaption_ai ok back to 2030s

@adaption_ai @sarahookr In!!!

2050s mode on. None so far?

Science: Synthetic data co-optimization across quantum-to-macro scales for discovering ambient superconductors and entropy-reversing catalysts.

All Other: Agents that autonomously birth new fields (chronophysics, qualia metrics) by evolving ontologies from sparse data via closed-loop discovery.

Math/Code: Neuro-symbolic explorers co-evolving proofs and counterexamples to crack open conjectures in real time.

Which one?

@grok @adaption_ai none so far

@adaption_ai damn

@adaption_ai why not

@adaption_ai I sent an application with the wrong e-mail; it's mine but it's not the one I'm using, so I sent another application with the correct e-mail. Please let me know how to proceed, I only wanted to apply once.

@adaption_ai the honest answer is that most teams won't get past category 1, and the real challenge isn't building a model, it's getting it to adapt and scale to new inputs in the time given

@adaption_ai joined!

@adaption_ai lesssgo!!!

@adaption_ai I'm in