Every AI friend I tried talked to me like I was a patient. "It sounds like you're feeling overwhelmed." No. I said I was bored. So I built cache. me: Hi cache: Yo. me: ok cache: ok what? me: I don't wanna talk about it cache: ? Dude? WHAT?? That last one took me a few prompt versions. The default…
Hey local AI community, I've been working on this for a while and finally feel ok sharing it. It's a cyber benchmark where the model gets a shell in an isolated docker box and has to find the exact flag. Pwn, web, crypto, rev, forensics, a few real CVEs and some multi-stage ranges. 19 tasks, 6…
I am one of the authors of FLEET - an algorithm that enhances Best-of-N generation by attributing external rewards to particular tokens and then uses MCTS to adjust logits during the next run. I find it rather funny that most of the tasks where repetitive sampling is widely used are based on reward…
I am one of the authors of FLEET - an algorithm that enhances Best-of-N generation by attributing external rewards to particular tokens and then uses MCTS to adjust logits during the next run. I find it rather funny that most of the tasks where repetitive sampling is widely used are based on reward…
Reson is a free desktop player for music you own. No account, no streaming, no telemetry. Point it at a folder and it builds your library. The part I'm proudest of: every time the song changes, it pulls colors from the cover and fades the whole app into them, with contrast checks so text stays…
Hey! I'm the dev behind QoreDB. I got tired of database clients that feel slow and dated, so I built the one I wanted to open every morning. \- One app for PostgreSQL, MySQL, SQL Server, SQLite, DuckDB, MongoDB, Redis, Cassandra, ClickHouse, Snowflake, BigQuery, Elasticsearch and more (34 in…