Fortran
PulseAugur coverage of Fortran — every cluster mentioning Fortran across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
CosineAI's Lumen Outpost coding model beats GPT-5.5 on niche languages
Fireworks AI announced that their partner CosineAI has developed a new coding model, Lumen Outpost, trained on specialized codebases like Fortran and Verilog. This model reportedly outperforms GPT-5.5 by over three time…
-
AI "slop" found in Fortran repository, user reports
A user on Mastodon has encountered what they describe as "AI slop" within a Fortran repository. They expressed a desire to avoid such content and subsequently blocked the user responsible.
-
New Agnostics pipeline boosts LLM coding in low-resource languages
Researchers have developed a new language-agnostic post-training pipeline called Agnostics, designed to improve the coding abilities of large language models in low-resource programming languages. This system bypasses t…
-
New LLM approach aids legacy code migration with declarative representations
Researchers have developed a new method, ADFD-Migrate, to assist in the migration of legacy software repositories by approximating the latent declarative representation of code. This approach uses an LLM to infer an ann…
-
AI translates legacy code to Rust for bioinformatics
Researchers have developed a method using agentic AI and static analysis to translate legacy bioinformatics code into the modern language Rust. This approach addresses issues with older code, such as maintenance costs, …
-
EvoX Genesis enables autonomous software evolution with persistent project framework
Researchers have developed a new framework called EvoX Genesis that enables autonomous software evolution by making the software project itself persistent, rather than relying on individual coding agents to persist. Thi…
-
EvoX Genesis enables autonomous software evolution with persistent projects · 4 sources tracked
A new research paper introduces EvoX Genesis, a system that organizes software development around a persistent project rather than persistent agents. This approach allows for long-horizon development, demonstrated by th…
-
Fortran transpiler FGPT bridges legacy code to JAX and NumPy
Researchers have developed FGPT, a novel transpiler designed to convert legacy Fortran code into modern Python frameworks like JAX and NumPy. This tool aims to bridge the expertise gap for scientists who are unfamiliar …
-
LLM inference engines see major speed boosts with new techniques and optimizations · 4 sources tracked
Several projects are enhancing the performance of local LLM inference engines. Kernel Acceleration (VK) has developed three engines (VKAE, VKUE, VKIE) that improve token generation speed by up to 601 tokens per second t…
-
Cybersecurity M&A: Prioritize Strategy Over AI Hype
Cybersecurity acquisitions in 2026 should prioritize strategic alignment and genuine innovation over mere AI integration, according to industry experts. Rohit Dhamankar of Fortra advises buyers to identify solutions tha…
-
Fortran code gains automatic differentiation via LFortran and Enzyme
Researchers have developed a method to enable automatic differentiation for legacy Fortran code, allowing it to be integrated into modern machine learning frameworks like JAX and PyTorch. This approach uses LFortran to …
-
AI readiness doesn't require ditching IBM i core systems
Organizations are debating whether to fully migrate from IBM i systems before adopting AI, a move that could be costly and disruptive. While IBM i is considered legacy due to its interface and limited native AI integrat…
-
LLM pipeline translates legacy Fortran code to JAX for scientific modeling
Researchers have developed a novel five-phase pipeline utilizing LLM-based agents to translate legacy Fortran code into the JAX framework. This system automates the process of code migration, including dependency analys…
-
AI Agent Converts Legacy Finite-Difference Code to Devito
Researchers have developed an AI agent framework designed to convert legacy finite-difference code into the Devito environment. This system utilizes Retrieval-Augmented Generation (RAG) and open-source Large Language Mo…
-
Sunya programming language bootstrapped with custom VM, not Fortran
The creator of the Sunya programming language, with assistance from Copilot, has decided against using Fortran for bootstrapping. Instead, they opted to build Sunya from scratch using a custom virtual machine and a seed…
-
Old programming article sparks debate on AI's role in coding
A user on Mastodon shared a historical artifact from the era of punch cards and Fortran programming, drawing a parallel between past programming practices and the current discourse surrounding AI in programming. The use…
-
Free Pascal and BLAS offer deterministic HPC for SLM projects
A user on Mastodon is exploring the use of BLAS, a set of Fortran-based matrix routines, for their Small Language Model (SLM) project. They express a preference for Free Pascal over languages like C, Python, Rust, and C…
-
I learned # Pascal in the 80s. I learned a bit C and Rust and hated that pointer logic which is extremely clumsy for matrix manipulation. # Python and # C users
A programmer shared their experience learning various programming languages, finding Pascal's array handling superior for matrix operations compared to C and Rust. They noted that libraries like NumPy are often written …
-
New research tackles LLM factuality, architecture inference, and specialized evaluation
Researchers are developing new methods to improve the accuracy and reliability of large language models (LLMs). Google Research has introduced SLED (Self Logits Evolution Decoding), a technique that leverages all layers…