#CapCode
Pilgrim Monument. Day & Night. #PTOWN #CapCode #photography #historicsights
August 23, 2025 at 1:12 AM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
September 21, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
April 14, 2025 at 4:30 PM
Coding agents are evaluated with unit tests:

more tests passed = better model.

But if tests or feedback are accessible, models may learn to game them.

We introduce CapCode to detect suspiciously high scores, and CapReward to discourage them during RL.

🧵1/10
June 23, 2026 at 1:03 PM
We know the chip isn't locked bc frequency and capcode configuration is one of the AR-924's big features. (Programming port is under the sticker in the top left in older models, Taiwanese model uses USB.)

With the manufacturer datasheet, a connection could be made between any suitable pin...
2/
September 22, 2024 at 3:20 PM
arXiv📈🤖
Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests
By Lodkaew, Ackermann, Nishimori et al
June 8, 2026 at 5:34 AM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
September 14, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
September 7, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
August 31, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
August 24, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
August 17, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
August 10, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
August 3, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
July 27, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
July 20, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
July 13, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
July 6, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
June 29, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
June 22, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
June 15, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
June 8, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
June 1, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
May 25, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
May 18, 2026 at 4:30 PM
18:30 TEST CAPCODE RANGE MELDKAMER OOST-BRABANT #p2000
May 11, 2026 at 4:30 PM