Masayuki Hatta (@mhatta) header
Masayuki Hatta (@mhatta) profile picture

A hacker wannabe from Japan. This account features my rants mainly in Japanese or English.

東京都練馬区
Joined April 2007
Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)Photo by Masayuki Hatta (@mhatta)
We interrupt our usual programming to inform you that I was never hired by Facebook to do a hit job on Jonathan Haidt. | Statistical Modeling, Causal Inference, and Social Science statmodeling.stat.columbia.e…
102
Testing Silicon Photonics at Scale | SEMI semi.org/en/blogs/testing-si…
1
122
Local Inference with LLMs · Jacques Mattheij jacquesmattheij.com/local-in…
110
Masayuki Hatta retweeted
Tested NODECODE against Codex CLI. Same model, same prompt, identical cloud VMs: build a playable 3D pelican kart racer, with up to 60 minutes to keep improving it. GPT-6.1 Terra: • Codex: 9:56, 3.29M input / 31.6K output tokens • NODECODE: 3:56, 226K / 13.0K GPT-6 Luna: • Codex: 20:29, 7.62M / 74.0K • NODECODE: 8:24, 1.07M / 23.8K All 4 games load, drive and pass my check. NODECODE used 7–14x fewer input tokens and finished 2.5x faster, but it also stopped earlier and its games are plainer. One run each.
Introducing NODECODE: an open-source agent that rewrites itself as it works. In LISP; the AI-native language. McCarthy imagined a program you’d improve “by making statements to it.” Now you can, it’s yours and it will evolve over time. MIT. Works in Discord, TG, etc. Built for cyber.
1
3
3
7
1,449