FRAMEWIREIndonesiaUpdated Sep 22Live wire
0:00 / 0:00

Claude Code ran out mid-task.

Codex finished it from a 3 KB note: 7 of 7 checks passed. Same repo, same Codex, told only "continue": 5 of 7. The note is written by Jev, not Claude, because once your limit is gone Claude can't write it. Claude Opus 5.5 sorted the same 112

Stanislav SorokinSep 22
0:00 / 0:00

[Breaking News] OpenAI releases GPT-6 Sol and Luna.

API price is half price compared to GPT-5.6. Fable 5.1 level score at about 1/10th the cost. It seems to be quite useful in actual combat. ・The price of 1 million tokens is Sol $2/$10, Luna $0.10/$0.50 ・AutomationBench is 33.2%. 26.9% higher than Opus 5 at approximately 1/11th the cost ・DeepSWE 1.1 is 68.8%. Fable…

チャエン | デジライズ CEO《重要AIニュースを毎日最速で発信⚡️》Sep 225
0:00 / 0:00

Opus 5.5 - in my opinion the best implementation of the task I have seen so far.

Perfect. Total cost: $19.86 Total duration (API): 52m 6s Total duration (wall): 4h 21m 14s (I left it for 3 hours of idle waiting - I was in the city) Total code changes: 2004

Remek KinasSep 2216
0:00 / 0:00

This is a classic one-up on opus 5

Amichai MantinbandSep 224