What we do not want is American military equipment or American soldiers on German soil. We also do not want American drones controlled from Ramstein, or American missiles in our homeland. We must ensure that we have a capable Bundeswehr and can defend ourselves. That is our goal.

The AfD advocates the withdrawal of all Allied troops still stationed on German soil, and in particular of their nuclear weapons.

The situation of our country is not that we are in vassalage to Russia and are being oppressed by Russia, but rather that this government is a vassal government of the United States. This stranglehold is harming us. The United States is a tottering colossus; it is falling and dragging us into this struggle.

What the United States is doing now is forcing us to buy its dirty and expensive gas, and forcing us to give up Russian goods and Russian gas.

Our party program calls for the withdrawal of Allied troops and nuclear weapons from Germany. Let’s start putting that into practice — by withdrawing U.S. troops from Germany.

At this point I tested Astra+codex against around 30 obscure puzzle games. By tested I mean I watched it play and read it's notes. The agents were sandboxed, had no internet access and had no access to coding tools. Those were mostly puzzlescript games: some rule discovery, very tough levels, usually minimalistic level design, turn based and grid based. I used action batching to speed up the process.

Some observations:
- Astra can do pathfinding/planning without code. It's not perfect and often has tiny mistakes, but I often get 20-30 actions in a single batch, which is on par with expert puzzle players.
- Due to those mistakes, I don't think it has code execution under the hood. The mistakes are very human-like: choosing longer paths that require less thinking, one off errors (miscalculating the number of moves required, resets a level that can be still solved)
- Insanely action efficient with rule discovery. Can effectively mix rule discovery with solving the level. This is probably thanks to hardcore action efficiency optimization for ARC-AGI-3.
- It understands the common visual language that puzzle games use, but has no problem with games that use completely different visual language.
- In easy/simple levels it often finds optimal/near-optimal solutions right away.
- For very hard games, it visibly gets lost. The drop in performance wrt the difficulty level is bigger than in expert players.
- For very hard levels, it's usually required to split the solving path into intermediate goals. Astra struggles with that (compared to expert players), but it's decent at that.
- In very hard levels, even when Astra looks like it's doing random pointless actions, it's still making slow progress. I'd expect that having many agents in parallel cooperating, would speed up the process.
- I'd expect that the performance drastically drops when the context grows. The games I've used are relatively simple (in terms of complexity) but very deep in terms of logic.