Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
TL;DR On August 5 I published a post-mortem of mlx.fast, an optimization competition I lost.
-
TL;DR mlx.fast is an open autoresearch competition: make a 21.6 GB mixture-of-experts model decode faster on Apple silicon without changing a single output token.
-
TL;DR Tool calling on local stacks breaks silently: the same model, at the same quantization, with the same prompt, can execute tool calls perfectly on one inference server and fail completely on another.
-
TL;DR I kept hitting the same wall when I let a planning model hand coding work to a separate executor model (OpenAI's Codex): the background jobs died.
-
TL;DR Google Research released TabFM on 2026-06-30, a zero-shot foundation model for tabular data: no training, no tuning, you hand it your table and it predicts.
-
TL;DR I took TurboQuant, a KV cache compression method from a 2025 Google Research paper (ICLR 2026), and tried to make it actually work for long-context retrieval on an Apple M1 Pro with 16GB of RAM.