Signed in
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
Welcome to Pump.fun!
Pump lets anyone create coins, giving everyone equal access to buy and sell from the start. Prices can move quickly, so trade carefully.
By clicking this button, you agree to the Terms and Conditions, Privacy Policy, and certify that you are over 18 years old.
We value your privacy
This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.
 Aktief | $440.02% |
 levin | $280.01% |
 poeen | $250.01% |
 piousdolphin846 | $180.01% |
 4ynRf1 | $170.01% |
 79QbRa | $140.01% |
 hunking | $80.00% |
 TNC1996 | $70.00% |
 Wesiris | $70.00% |
 5Z7rSZed | $60.00% |
 jesusdvdfg | $60.00% |
 Caseyz | $60.00% |
 tendershrimp412 | $40.00% |
 DF3czZ | $40.00% |
 TlstBoy | $40.00% |
| $30.00% | |
| $30.00% | |
 DyBpoz | $20.00% |
 nigga68 | $20.00% |
 3v5Nco | $20.00% |
 Ukmera | $20.00% |
 flamingorca6305 | $20.00% |
 cwvcubfra | $20.00% |
 44VooW | $20.00% |
 DbE7qT | $20.00% |
| $20.00% | |
 ChTBAdj | $20.00% |
| $10.00% | |
 TheRuneBistro | $10.00% |
 3URhvJ | $10.00% |
 Backstein | $10.00% |
 yeray | $10.00% |
 Woodchuck | $10.00% |
 7yxgHn | $10.00% |
 ao3c3f4a | $10.00% |
| $0.990.00% | |
 82EN4s | $0.960.00% |
| $0.960.00% | |
| $0.940.00% | |
 grwnner | $0.780.00% |
 Tiborius | $0.780.00% |
| $0.760.00% | |
 9dYh3L | $0.750.00% |
 smpns | $0.740.00% |
 vainstarfish716 | $0.720.00% |
 Slatt51er | $0.710.00% |
 stefcoin | $0.670.00% |
 Ha2AgB | $0.430.00% |
 79qnu9 | $0.420.00% |
 Hedera | $0.420.00% |
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL) 🦭, a framework that enables LLMs to self-adapt by generating their own finetuning data and update directives. Given a new input, the model produces a self-edit — a generation that may restructure the information in different ways, specify optimization hyperparameters, or invoke tools for data augmentation and gradient-based updates. Through supervised finetuning (SFT), these self-edits result in persistent weight updates, enabling lasting adaptation. To train the model to produce effective self-edits, we use a reinforcement learning loop, using the downstream performance of the updated model as the reward signal. Unlike prior approaches that rely on separate adaptation modules or auxiliary networks, SEAL directly uses the model's generation to parameterize and control its own adaptation process. Experiments on knowledge incorporation and few-shot generalization show that SEAL is a promising step toward language models capable of self-directed adaptation in response to new data.
