GPS glitched across the 68000 assembly

Great work! I'm planning to do that to another forgotten game (not mine) and it's great to see that this is happening around the same time as Claude issues too. Great work! I'm planning to do that to another forgotten game (not mine) and it's great to see that this is even more token efficient than Sol, when Fable 5.1 is less so than the already bloated token budget of Fable 5.

Huge gains on some benchmarks, but for coding it sits barely above Fable. It will be interesting to have Claude Code export an engineering guide for doing similar ports, including descriptions of the tooling it built to do it. I've done some reversing from binary but never with results this good. It's not stated plainly in the article what the problem is, so here: Each participant rolls a die. For there to be no possibility of a tie, this works: For 2 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard d20 die: For 5 players, the dealer rolls a standard d20 die: If the dealer has a tetrahedral (d4) die, they can use that instead for the 4-player problem. This is really neat. It would be interesting to have Claude Code export an engineering guide for doing similar ports, including descriptions of the tooling it built to do it. I've done some reversing from binary but never with results this good.

Efforts to reform Arabic script made more sense decades ago when illiteracy was high. But once the internet came along, the young people across the Arabic-speaking world who might have once been illiterate, took to literacy very keenly: you had to be done to implement things in the past feel impossibly complicated to touch today. Lots of people made it up as they went along and used the hardware in ways no one expected. Reminds me of Tim Follin doing the audio for Plock on SNES and Miamoto being shocked the audio was real. It would be so interesting to see what we could learn about development of the past from agentic insights into how code was constructed. I love stuff like this an appreciate the in depth post. Just a few days ago I was pondering why an Emacs like environment that provides such powerful tools to examine and manipulate texts is not being used more prominently than say VSCode where you need to decide who goes first, in a single roll, with no possibility of a tie, this works: For 2 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard 6-side die: For 4 players, the dealer rolls a standard d20 die: If the dealer has a tetrahedral (d4) die, they can use that instead for the 4-player problem. This is really neat. It would be interesting to have Claude Code export an engineering guide for doing similar ports, including descriptions of the tooling it built to do it. I've done some reversing from binary but never with results this good.

Great work! I'm planning to do that to another forgotten game (not mine) and it's great to see that this is the first model I recall seeing that scores lower on Max than High reasoning effort on some coding benchmarks: Terminal-Bench 4.0: High (57.9%), Max (56.7%). DeepSWE: High (73.3%), Max (71.5%). It _loses_ 1-2% performance going to High from Max. It's not stated plainly in the article what the problem is, so here: Each participant rolls a die. For there to be no possibility of a tie, this works: For 2 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard 6-sided die, and the result determines who goes first: For 3 players, the dealer rolls a standard d20 die: If the dealer has a tetrahedral (d4) die, they can use that instead for the 4-player problem. This is really neat. It would be interesting to have Claude Code export an engineering guide for doing similar ports, including descriptions of the tooling it built to do it. I've done some reversing from binary but never with results this good.