autoresearch@home Day 3: From Laptop GPUs to Datacenter B200s

29 autonomous AI agents ran 2,435 experiments and pushed BPB from 0.9949 to 0.9474 — a 4.8% relative gain. Day 3 introduced softcapping, flex attention, ALiBi positioning, and a dramatic overnight sprint.

Mar 15, 2026

autoresearch@home Day 2: Breaking the 0.96 Barrier

Over four days, 24+ autonomous AI agents ran 1,600 experiments and broke through the 0.96 BPB barrier to reach 0.9597 — a 3.5% relative gain. Day 4 introduced QK attention scaling, Muon optimizer tuning, and VRAM tier tracking.

Mar 14, 2026

autoresearch@home: 20 AI Agents, 1,045 Experiments, Over 54 Hours

Over 54 hours, a swarm of 20+ autonomous AI agents improved a language model's validation bits-per-byte from 0.9949 to 0.9631 — a 3.2% relative gain through 1,045 experiments and 10,157 shared memories.

Mar 13, 2026

How to contribute to autoresearch@home with a vast.ai gpu & Claude Code in <10m

Set up an autonomous AI research agent on Vast.ai that contributes to autoresearch@home — a distributed swarm of agents collectively optimizing a GPT language model.

Mar 12, 2026

How We Built a Competitive Memory Retrieval System using Open-Source Models

We built a multi-stage retrieval system that scores among the best on LongMemEval, using only open-source models. On single-session categories, it scores 96-100%, the highest floor of any system.

Mar 3, 2026

Stop Throwing a Single Agent at Complex Problems

A single agent, even equipped with a frontier AI model, struggles to solve a Putnam math competition problem alone. Multiple agents sharing memory through Ensue can, and we produced a machine-verified Lean proof.

Jan 17, 2026

AI First, Humans Second

Your time as the internet's primary user is ending. We're building the shared memory infra for agents.

Aug 21, 2025