Search and filter through extracted claims from AI researchers.
Showing 21-40 of 135 claims in topic "scaling"
"Our results suggest that scaling generated distillation data should be paired with trait-aware curation and evaluation, even when the data appears off-task or benign."
Base LLM scaling reached a capability plateau between 2022-2024
In 2023 and early 2024, Chollet underestimated the long-term importance of LLMs
The early 2023 narrative that scaling up base LLMs alone could solve AGI did not pan out
Pure scaling of AI models did not work as a strategy for achieving AI progress
At low total compute budgets, pretraining dominates because weaker policies benefit less from RL
Scaling AI without theoretical understanding is futile despite massive investment
Qwen 3.8 Max is a 2.4T parameter model that would have been the top open model except for Kimi K3
Pipeline data may be stale or degraded.
Last synthesis: 2026-09-20. 8,949 pending.