Towards Efficient Threat Intelligence Instruction Tuning via Quality-Aware and Optimal Transport-Guided Data Selection
CTI-TDS selects compact, high-quality instruction data for threat-intelligence model tuning.
Stories per day · 30 days
2 RSS
Relatedcareer1cti1ctibench1data-selection1hacker-news1instruction-tuning1opinion1optimal-transport1software-engineering1
15 stories, newest first · one card per story
Stories tagged #llms
Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
LASEF finds English reasoning skeletons help smaller models slightly, but language choice is context-dependent.
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
TextReg curbs prompt overfitting, gaining up to 16.5% out-of-distribution accuracy over REVOLVE.
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation
A controlled study finds LLMs often miss latent sequential rules despite matching surface action frequencies.
The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models
A primitive-based diagnosis finds Discovery is the main bottleneck in LLM mathematical reasoning and shows it can be repaired.
GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price
Simon Willison says GPT-6.1-Sol pelican drawings look similar to other GPT-6 family results.
2026 in LLMs (so far)
Simon Willison's WeAreDevelopers keynote surveys 2026 LLM trends, starting with Claude Opus 4.5 and GPT-5.1.
Note on 24th September 2026
Willison argues coding agents raise the skill and discipline needed to engineer software well.
Using LLMs to trace alchemical knowledge and decode 17th century letters
A historian says frontier models traced alchemical sources and broke an unsolved 1941 cipher.
Learning to Discover Interesting Mathematics
A 27B model ranks mathematical theorems by interestingness and cuts Mathlib overlap from 91.9% to 30.6%.
Note on 18th September 2026
Simon Willison argues that ignoring LLMs today is like a geneticist dismissing the newly opened Jurassic Park.
I Don't Like LLMs
Martin Fowler publishes an opinion essay titled 'I Don't Like LLMs' laying out his skepticism about large language models.
Quoting Laurie Voss
Laurie Voss argues AI collapses code-writing and review costs, leaving product discovery and precise definition as the core of software engineering.
Quoting Paul Ford
Simon Willimon quotes Paul Ford arguing AI can write good software but cutting-edge work still demands human collaboration, craft, and judgment.
Introducing GPT-6 Astra for developers
OpenAI introduces GPT-6 Astra for developers, with improved attention to detail, prompt understanding, and notably strong 3D model generation.