#token-generation

[ follow ]
fromTheregister
2 weeks ago

Boffins detail new algorithms that boost AI perf up to 2.8x

Speculative decoding offers a new way to increase token generation rates significantly, achieving up to 2.8 times faster performance while avoiding the need for specialized draft models.
Artificial intelligence
Growth hacking
fromHackernoon
5 years ago

From TikTok to TGE: How Wunder's Ryan Martin Pulled Off a Web3 Miracle in Six Months | HackerNoon

Wunder's CMO Ryan Martin leveraged his unique marketing experience to launch the company's token in only six months.
fromHackernoon
1 year ago

Why iOlyWorld Is One of the Most Anticipated Web3 Gaming Projects of 2025 | HackerNoon

Originally an NFT-focused project, iOlyWorld has evolved into a broader Web3 gaming platform integrating blockchain, AI, and interactive storytelling, targeting gamers and creators.
Online Community Development
fromHackernoon
1 year ago

LLM Service & Autoregressive Generation: What This Means | HackerNoon

LLMs generate tokens sequentially, relying on cached key and value vectors from prior tokens for efficient autoregressive generation.
fromCoindesk
11 months ago

Pump.Fun's Removal of $2 Issuance Charge Pushes Daily Fees to All-Time Highs, But Users are Unhappy

Pump.Fun has set a record by generating $5.3 million in fees over 24 hours, leading the crypto token generation market.
[ Load more ]