Unverified50% confidenceBenchmarkExact time
In the Native AOT test, REA loaded the 1.1 MB pure x64 executable into Ghidra, Ghidra found 3627 functions (almost all of them .NET runtime), and the AI restored the entire application after about 18 minutes, including the same weights, dithering, and key.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedLiquid AI d1-omni-600M 参数规模为 587M，Q8_0 GGUF 量化后约 670 MB，llama.cpp 已合并支持，可在树莓派 5 上通过 llama-server 命令运行。63% similarUnverifiedAplomb 1 权重以 bf16 精度运行，参考脚本下约需 12 GB 显存即可运行63% similarUnverifiedGB200 NVL72在FP8精度下的AI算力可达1.44 ExaFLOPS62% similarUnverifiedIQ4_XS量化文件大小15.57GB，pp2048为95.4 tok/s，tg128为10.9 tok/s62% similarUnverifiedThe author's generation setup is an RTX 5070 Ti GPU with 32GB of RAM, 20 sampling steps, approximately 53 seconds per iteration, resolution set to 0.6, aspect ratio 1:1, and no turbo LoRA used.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1034580API
curl https://kongchang.com/api/v1/knowledge/claims/1034580MCP
get_claim(id=1034580)