An experienced senior developer who frequently uses AI and coding agents questions how their job will evolve in the coming years, seeking advice on which skills will remain valuable as AI advances.…
A Hacker News user asks whether developers' test suites meet the standard that passing tests guarantees code cannot break, sharing that they have found AI tools to work flawlessly when this bar is met…
MnesticDB, a fork of the dormant CozoDB, adds bitemporal provenance and semiring provenance to enable auditable, time-travel-capable agent memory. The database tracks both valid time and transaction t…
A Hacker News user claims that Anthropic's Claude Opus model has been 'nerfed,' reporting degraded performance and failure to follow instructions over the past week.…
A Hacker News user asks whether single-task focus is outdated in the AI era, noting that AI makes parallel work easier but deep focus may still be more effective for quality work.…
A developer created a CLI tool called Coder that delegates coding tasks to Codex and Claude engines, enabling Claude Code to spin up Codex agents for individual tasks while keeping context clean and s…
A Hacker News user asks the community about real-world use cases for the 'max mode' or 'Ultra mode' settings on frontier AI models like ChatGPT and Claude Fable, noting that in their software developm…
A Hacker News user reports that coding agents using large language models spend over 90% of their time re-reading context, with an estimated 20% of that context being irrelevant to the task. The user …
A Hacker News user expresses despair about the future, claiming AI owners are exploiting workers and that AI surveillance is expanding, while politicians aligned with tech interests fail to act. The p…
A Hacker News user asks whether people would play games developed with AI, noting that they have used frontier AI models to recreate simple mobile games without ads or microtransactions for personal u…
Cactus released version 2 of its on-device AI inference platform, featuring model confidence-based routing to cloud fallback, lossless 4-bit quantization, and GPU acceleration on Apple Metal. The plat…
A Hacker News user asks the community to share specific tasks from the past month where open-weight models like GLM, DeepSeek, Kimi, or Qwen failed but frontier models like Opus, Fable, or GPT succeed…
Andrej Karpathy has been largely inactive on social media and GitHub since joining Anthropic nearly two months ago, raising questions about whether his reduced public presence is beneficial for the AI…
A Hacker News user asks how developers navigate unfamiliar codebases, noting they use LLMs for high-level overviews but find them cumbersome for detailed understanding, and seeks better tools for trac…
A Hacker News user asks whether others have successfully generated authentic drawing styles, including scribbles and hand-drawn looks, using AI apps.…
A user on Hacker News is seeking scent ideas for a candle that would smell like burned LLM tokens, as a birthday gift for a data engineer relative. Suggestions from the community include burned toast,…
A Hacker News user questions the relevance of Vim in the age of AI-assisted coding, noting they look at code less frequently and wonder if the editor still makes sense.…
A Hacker News user argues that large language models (LLMs) are inherently bad at generating novelty, which presents an opportunity for humans to focus on creative and innovative work. The author envi…
A developer asks whether safe wrappers are being built around database operations to allow AI agents to access production data without risk.…
A developer is seeking recommendations for AI translation platforms to localize food recipes and menus into 30-50 languages, prioritizing accuracy and natural wording over cost, with local execution a…