The player’s current scrap is not 30; it is 10 (see the number next to the scrap icon in the top left-center, or here). The only place with the number 30 is the ‘current hull’ indicator, which isn’t related to the scrap amount at all. Steven and Dre Hozer are also humans, not rock-like Engi (see the human and Engi icons on the FTL wiki to see the difference).
Note that while these are seemly ‘minor’ errors compared to e.g. trying to use Tesseract on this image, they still mostly prevent modern VLMs from just playing FTL like a human would. I have also been messing around with AIs on non-game UI contexts too, and I’ve also seen weird behavior there too. For example, Gemini 2.5 Flash can’t do an accurate segmentation of the Google AI Studio UI, instead hallucinating a previous version of it, but it can accurately transcribe it in a regular chat session. However, it seems like most VLMs can transcribe most web UI elements effectively (unlike in at least one game); more study is required to figure out why, obviously.
Im not sure what you’re trying to transcribe from this image, but Gemini seemed to do it just fine:
Of course. Here is the information from the store interface in the image, presented as a series of text tables.
The player’s current scrap available is 30.
For Sale: Items
| Item | Quantity Available | Price (per unit) |
|---|---|---|
| Drone Parts | 5 | 3 Scrap |
| Missiles | 4 | 6 Scrap |
| Drone Parts | 3 | 8 Scrap |
For Sale: Augmentations
| Augmentation | Price |
|---|---|
| Hacking Stun | 60 Scrap |
| FTL Recharge Booster | 50 Scrap |
| Explosive Replicator | 60 Scrap |
For Hire: Crew
| Name | Species | Price |
|---|---|---|
| Dre Hozer | Engi | 45 Scrap |
| Steven | Engi | 45 Scrap |
| Thomas Bloch | Mantis | 55 Scrap |
Services
| Service |
|---|
| Repair 1 Hull Point |
| Repair All Hull |
The player’s current scrap is not 30; it is 10 (see the number next to the scrap icon in the top left-center, or here). The only place with the number 30 is the ‘current hull’ indicator, which isn’t related to the scrap amount at all.
Steven and Dre Hozer are also humans, not rock-like Engi (see the human and Engi icons on the FTL wiki to see the difference).
Note that while these are seemly ‘minor’ errors compared to e.g. trying to use Tesseract on this image, they still mostly prevent modern VLMs from just playing FTL like a human would. I have also been messing around with AIs on non-game UI contexts too, and I’ve also seen weird behavior there too. For example, Gemini 2.5 Flash can’t do an accurate segmentation of the Google AI Studio UI, instead hallucinating a previous version of it, but it can accurately transcribe it in a regular chat session. However, it seems like most VLMs can transcribe most web UI elements effectively (unlike in at least one game); more study is required to figure out why, obviously.