Fortran
PulseAugur coverage of Fortran — every cluster mentioning Fortran across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
AI accelerates cyber threats, demanding faster security testing
The increasing accessibility of AI tools has significantly accelerated the timeline between vulnerability disclosure and exploitation, shrinking the window from weeks to minutes. This shift necessitates a higher maturit…
-
AI agents' tool interaction and code review methods explored · 4 sources tracked
Developers are exploring new methods for AI agents to interact with tools and code. One approach focuses on providing clear tool descriptions and automated checks to ensure agents use tools correctly, drawing parallels …
-
AI agents autonomously modernize legacy Fortran code for HPC
Researchers have developed an autonomous AI workflow capable of modernizing legacy Fortran codebases for high-performance computing (HPC) environments. This agentic system uses specialized large language models (LLMs) t…
-
OpenAI's GPT-6 shows improved coding for legacy systems
OpenAI claims its new GPT-6 models demonstrate significantly improved code generation capabilities, particularly for legacy programming languages like COBOL, Fortran, and Visual Basic. These languages are crucial for ma…
-
OpenAI's GPT-6 shows major gains in legacy programming language support
OpenAI has significantly enhanced its latest AI models, particularly GPT-6 Astra and GPT-6.1 Sol, in their ability to handle legacy programming languages. GPT-6 Astra achieved an 87.4% pass rate across 20 languages on t…
-
OpenAI models improve COBOL translation for bank system migration
OpenAI has announced that its AI models are now significantly better at understanding and working with legacy programming languages like COBOL, Fortran, and Visual Basic. This development is crucial for banks, as 40% st…
-
OpenAI's GPT-6 Astra shows strong coding performance in COBOL and Fortran evaluations
OpenAI has released new evaluations for its GPT-6 Astra model, showcasing its performance on coding tasks in COBOL and Fortran. GPT-6 Astra achieved an 87.4% success rate on the MultiLangBench test, a benchmark involvin…
-
Python AI development still relies on Fortran, compiler evidence suggests
The use of AI models built on Python can be traced back to the foundational Fortran programming language. Specifically, the installation process for many Python AI packages involves the Gnu Fortran 77 Compiler (g77), hi…
-
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…