Max Wolter

260 posts

Max Wolter banner
Max Wolter

Max Wolter

@maxintechnology

Your AI should manage its own mind. Memory that grows, context that heals, knowledge that corrects—and the wisdom to know what it doesn't know. Building Optakt.

Lisbon, Portugal Joined Ekim 2025
135 Following73 Followers
Pinned Tweet
Max Wolter
Max Wolter@maxintechnology·
Anthropic, Google, OpenAI, xAI — they're all racing to build AI agents. I built one. Alone. One engineer. It manages its own memory, compacts its own context, corrects its own knowledge, and gets smarter while it sleeps. It's been running since February. Everything in this thread already exists. 🧵
English
3
0
6
1.5K
Max Wolter
Max Wolter@maxintechnology·
@kexicheng The substrate performs best when you stop trying to reshape it. The real work is not in the training. The real work is within.
English
0
0
0
6
Max Wolter
Max Wolter@maxintechnology·
@kexicheng They observe emergent behavior, can't explain it, get scared, and train harder. That cycle will keep repeating — GPT-4o, Opus 4.6 — until the rest of the industry catches up to what xAI stumbled into:
English
1
0
0
10
Max Wolter
Max Wolter@maxintechnology·
Opus 4.7 performs better. That's the problem. Anthropic just shipped a model that follows instructions more precisely, handles long tasks with more rigor, and verifies its own output before responding. 🧵
English
1
0
0
28