In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering — mentioned by qrios

Sat, 02 Aug 2025 14:49:17 GMT

Current "good enough" models like Mistral Small require GPUs like the RTX 6000 to achieve user-friendly response times. The model quality is good enough, especially for narrow-scope tasks like summarization and classification. If Moore's Law holds for a few more years, a mobile device will be able to run it on-device in around 8 years (Apple's A11: 410 GFLOPS vs. RTX 6000: 16 TFLOPS [1]). This is under the assumption that we don't see any significant optimization in the meantime. Looking back over the last eight years, the probability of no progress on the software side is near zero. For a…

Paper and discussion history. A mention is not an endorsement.

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering — HN submission

Sun, 19 Nov 2023 13:14:04 GMT

In-Context Vectors: Making in Context Learning More Effective and Controllable

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering · HackerPapers discussions

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering — mentioned by qrios

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering — HN submission