According to @AnthropicAI, when controlling for general capabilities, models trained with SGTM perform worse on the undesired forget subset than models trained with data filtering, highlighting a reported performance gap between these unlearning approaches on targeted knowledge removal tasks, source: https://twitter.com/AnthropicAI/status/1998479611945202053. For trading context, the verified takeaway is the relative underperformance of SGTM versus data filtering on the forget subset under equal capability control, with no specific assets or tickers mentioned in the source, source: https://twitter.com/AnthropicAI/status/1998479611945202053.

According to @AnthropicAI, its study tested whether SGTM can remove biology knowledge from models trained on Wikipedia (source: Anthropic @AnthropicAI, Dec 9, 2025). According to @AnthropicAI, the team cautions that data filtering may leak relevant information because non-biology Wikipedia pages can still contain biology content (source: Anthropic @AnthropicAI, Dec 9, 2025). According to @AnthropicAI, the post does not provide quantitative results, timelines, or any mention of cryptocurrencies, tokens, or market impact (source: Anthropic @AnthropicAI, Dec 9, 2025).