Volodymyr Kyrylov
@darkproger
unsupervised learning and rl
가입 April 2008
2.5K 팔로잉 중 2.7K 팬
spark is close to an order of magnitude latency improvement for token output, now tools are the bottleneck. great for networks of codex exec
GPT-5.3-Codex-Spark is now in research preview.
You can just build things—faster.
