#python#agent#llm#llm_agent#llm_reasoning#machine_learning_systems#mlsys#reinforcement_learning#rl
AReaL is a free, open-source system for fast asynchronous reinforcement learning to train large AI models in math, coding, search, and agents. It decouples generation and training for up to 2.77x speedup, stable performance, and easy setup on single or 1000+ GPUs with algorithms like GRPO/PPO. Install via git/pip, run examples like GSM8K math instantly. You benefit by building top AI agents affordably and quickly, reproducing results with shared data/models, saving time/money vs. slow synchronous tools.
https://github.com/inclusionAI/AReaL
Lookonchain | ꘜ
An #Ethereum ICO participant who bought 100K $ETH(costing $31K) sold 4,283 $ETH($18.97M) again recently.
He has sold 44,284 $ETH($105M) at an average price of $2,378 since 2021, leaving 55,716 $ETH($261.6M).
The total profit is ~$366.8M, an 11,835x return!
https://etherscan.io/address/0x815c53bf36a3bc8b066715da459b365e6ce6c3ed
https://etherscan.io/address/0x2c06dd922b61514aafedd84488c0c28e6dcf0e99
Lookonchain | ꘜ
An #Ethereum ICO participant who received 20,000 $ETH( cost $6,200, now $86.6M) just sold another 2,300 $ETH($9.91M) 20 minutes ago, leaving him with 1,623 $ETH($6.99M).
https://x.com/lookonchain/status/1729788901756211328