Quint (@quint-lang.org)

Quint, an executable specification language for reliable systems

Quint is an executable specification language. Write specs you can run, simulate, and verify, so subtle bugs get caught before reaching production.

Understanding Spec-Driven-Development: Kiro, spec-kit, and Tessl

Notes from my Thoughtworks colleagues on AI-assisted software delivery

Priivacy-ai/spec-kitty

Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.

What spec-driven development gets wrong

The most powerful AI software development platform with the industry-leading context engine.

Apple Intelligence Foundation Language Models Tech Report 2025

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and…

The Emacsification of Software

We’re all reading a ton of Markdown. It’s been the lingua franca of software development since long before LLMs. But now agents have led us into a cursed renaissance of TUI tooling, and the reading experience has become intolerable. I’m certain that at least 14% of the agita about AI code is driven by exhaustion over incessantly scrolling terminal Markdown.

brexhq/prompt-engineering

Tips and tricks for working with Large Language Models like OpenAI's GPT-4.

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Large Language Model (LLM) agents have been widely adopted in modern software development workflows. SWE-bench [13] and related works [23, 24, 22, 25, 15] establish the task of issue resolution as a de-facto standard for assessing their capability and usefulness. In this setting, an agent is given an entire codebase, a task description (e.g., a bug report or feature request) in natural language and is instructed to produce a code patch that resolves the issue and passes the repository’s test suite. These benchmarks have been instrumental in demonstrating both the substantial potential and the persistent limitations of current models as SWE agents.

INIYSA on Twitter / X

Apple's on-device SLM, while not as strong in simple multilingual tasks as Google's Gemma 3 4B (3.3GB, 5GB in memory), seems to outperform Qwen3 4B or Phi 4 mini reasoning. It's very very impressive, especially considering its extremely reduced size of around ~1.4GB— INIYSA (@lafaiel) June 10, 2025

\robotoslablightdots.tts Technical Report

Text-to-speech (TTS) systems have largely solved intelligibility on standard read-speech benchmarks. What users expect from a modern system is broader: expressive and controllable output, real-time synthesis, and coverage of neutral reading, emotional dialogue, paralinguistic events, singing, and general audio. Current systems pursue this goal along three roughly distinct technical routes, and each route has its own unresolved problem.

The Kaitchup – AI on a Budget | Benjamin Marie | Substack

Weekly tutorials and news on adapting large language models (LLMs) to your tasks and hardware using the most recent techniques and models. The Kaitchup proposes a collection of 180+ AI notebooks regularly updated. Click to read The Kaitchup – AI on a Budget, by Benjamin Marie, a Substack publication with tens of thousands of subscribers.

LLMs as Collaborators in Language Specification and Design (PLSS 2026) - SPLASH/ISSTA 2026

Workshop on Programming Language Standardization and Specification This workshop aims to foster cross-pollination between researchers and industry professionals with experience in programming language specification and standardization. It provides a forum where participants can share insights, case studies, and best practices, and collaboratively explore solutions to current challenges. The goal of the workshop is to improve the collective understanding of how programming languages are specified, standardized, and evolved in practice. The workshop examines specifications as the foundation ...