Imported

313 posts in this topic

RSS All Topics Community
Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Community post

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across complex domains. The driver of this process is effective exploration, however, managing and improving exploration strategies remains a major bottleneck. Current systems face a fundamental dilemma: fixed strategies fail to adapt as search spaces scale, while online policy optimization requires navigating vast meta-search spaces under delayed and expensive feedback over long-horizon rollouts. We introduce \textsc{Dream-RSI}, a framework for...

1 min read W WebNovare Imports

Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across complex domains. The driver of this process is effective exploration, however, managing and improving...

Accurate Models of AMD Matrix Cores

Community post

Accurate Models of AMD Matrix Cores

Matrix multipliers available on recent GPUs do not conform with the IEEE 754 floating point standard. Features of matrix multipliers differ across vendors and architectures of the same vendor, such as accumulator width, rounding behaviour, normalisation points, intermediate underflow and overflow logic, the handling of subnormals, and the treatment of special inputs. As a result, reproducibility of small matrix multiplier results across devices is not possible and cannot be achieved by software control. Implementation details of matrix multipliers are not documented, making it difficult to...

1 min read W WebNovare Imports

Matrix multipliers available on recent GPUs do not conform with the IEEE 754 floating point standard. Features of matrix multipliers differ across vendors and architectures of the same vendor, such as accumulator width, rounding behaviour, normalisation...

Small programming tricks

Community post

Small programming tricks

Day to day, I think a surprising amount of engineering productivity comes from small nuggets of knowledge: being aware that a language feature exists; knowing that an unexplained tcp delay is probably related to the TCP_NO_DELAY setting and Nagle’s algorithm; knowing the right git incantation to get out of a pickle; or knowing a trick with sed to rewrite a file.

1 min read W WebNovare Imports

Day to day, I think a surprising amount of engineering productivity comes from small nuggets of knowledge: being aware that a language feature exists; knowing that an unexplained tcp delay is probably related to the TCP_NO_DELAY setting and Nagle’s...

DeepSeek v4.1 Flash

Community post

DeepSeek v4.1 Flash

🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models. 1/6

1 min read W WebNovare Imports

🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient. 🔹 Introducing the smallest model in our new architecture family, with native visual understanding. 🔹 Designed for greater capability, faster inference, higher throughput, and scaling...

Hitachi launches CO2 heat pump water heaters with solar-friendly tariff controls

Community post

Hitachi launches CO2 heat pump water heaters with solar-friendly tariff controls

Hitachi has introduced its Y-series EcoCute CO2 heat pump water heaters in Japan, with 370-liter and 460-liter models set to launch from November 2026. The upgraded range adds expanded support for daytime electricity tariffs and PV-linked energy management, alongside a five-year manufacturer warranty.

1 min read W WebNovare Imports

Hitachi has introduced its Y-series EcoCute CO2 heat pump water heaters in Japan, with 370-liter and 460-liter models set to launch from November 2026. The upgraded range adds expanded support for daytime electricity tariffs and PV-linked energy management...

Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Community post

Cognition launches new SWE-2 model, Rivaling Fable 5.1 and GPT-Astra

Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort…

1 min read W WebNovare Imports

Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort… Source: cognition.com (48 points, 9 comments) Hacker News discussion