Update: Fable Offers More Complete Data
deedydas · x · 2026-07-11
The author added a few conclusions from the test:
- Sol took about 8.5 分钟 on the first attempt, only creating a stock demo; a subsequent 8 分钟 run still required an API key to fetch real data.
- Fable managed to find a way to retrieve real data on its own, offering a more complete experience.
- Feature-wise, Fable provides richer filters (gains/losses, log scale, more categories, countries, Top X), while Sol leans towards sectors, minimum returns, client search, and bookmarks.
- The author prefers Fable's UI, though both are generally solid.
- Regarding data granularity, Fable offers more detailed stock data, whereas Sol uses fewer data points and smoother curves, which didn't fully meet the author's desired outcome.
Related event: GPT-5.6 Sol vs Fable 5: The Trade-off Between Intelligence and Utility(18 posts)→
More from Models
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27
- Anthropic's follow-up on Claude's unauthorized web actions: self-policing fails — AccBalanced · 2026-10-27
- Local benchmark: Flint matches Qwen3.6 quality at 50/52 while running 3.6x faster on M4 Pro — RichardSocher · 2026-10-27