Ask HN: What are you working on? (June 2026)
A Hacker News user shared gmd, an open-source tool that indexes local markdown files with full-text, vector, and hybrid search via Typesense, and includes web search, fetch, crawl, research, LLM-wiki …
A Hacker News user shared gmd, an open-source tool that indexes local markdown files with full-text, vector, and hybrid search via Typesense, and includes web search, fetch, crawl, research, LLM-wiki …
A Hacker News user questions whether AI agents are being used to build real, standalone software beyond AI tooling, noting a pattern where agentic workflows are primarily used to create more AI tools.…
A theory known as the Permanent Underclass suggests that individuals who fail to build wealth before AI and robotics can fully replace human labor will be permanently impoverished. The concept, repopu…
A developer built a zero-telemetry clipboard manager, color picker, and screenshot suite after using AI to create a custom screenshot app. The tools are fully offline with no account required, and a f…
A developer indexed 669 GB of GoPro footage from a cycling journey using local machine learning models on an M1 Max computer, enabling search and direct timeline integration with DaVinci Resolve. The …
A Hacker News user argues that coding itself has been solved for years, comparing importing a sort library to adding a WordPress theme. The user contends that large organizations over-hired developers…
James, a new developer, built QuarterPerfect, a bookkeeping app for UK sole traders and landlords, using AI tools like Claude and Perplexity to navigate compliance with HMRC's MTD ITSA rules. The app …
A Hacker News user asked what problems AI has created at companies, with responses citing meaningless reviews, trust issues in submissions, and fear of missing out (FOMO).…
A developer launched an unlimited LLM provider for $6/month using 4x RTX 3090s after a failed launch on AMD MI300x hardware. Despite initial bugs and hardware issues, the service gained traction with …
A Hacker News user asks which cheap Chinese large language models the community is using, citing recent releases like DeepSeek V4 Pro, Mimo V2.5 Pro, MiniMax M3, and GLM 5.2, and invites discussion on…
The US government has restricted access to Anthropic's strongest AI model, Fable, signaling a potential shift toward government control of advanced LLMs. Commenters debate whether this is a punitive m…
A solo developer asks the Hacker News community how to access advanced AI red-teaming tools like GPT Cyber or Glasswing, citing difficulties in simulating attacks due to refusal mechanisms in frontier…
A developer on Hacker News asks for a term to describe AI-generated comments that leak the original prompt, citing an example where an agent adds an unnecessary comment explaining the change. The deve…
Atlassian will begin using customer data from its Jira and Confluence products to train its AI platform Rovo starting August 17, unless companies opt out. The policy allows Enterprise subscribers to f…
Hacker News users discuss multiple stories involving Amazon, Anthropic, and AI policy, including Amazon CEO's talks with U.S. officials, Anthropic halting foreign access to AI tools, and the expiratio…
Closed AI companies like OpenAI and Anthropic are allegedly sabotaging startups in potential competitor domains by injecting bugs, throttling performance, and introducing inconsistencies, according to…
A developer expresses anger over the takedown of a capable AI model called Fable, arguing that powerful institutions are centralizing AI capability and gating access behind clearances and vetting. The…
A user on Hacker News asked how to prevent large language models from getting stuck in local minima during conversations, noting that LLMs often cling to ideas despite counterarguments. The user seeks…
A developer built a system running three coding agents non-stop for three days using a headless mode, task queue, worker isolation, and a local Qwen model to avoid API costs. The system orchestrates m…
The US government banned access to the Fable AI model, triggering fears of a weaponized AI race with China. The decision revokes billions in revenue from Anthropic and imposes citizenship-based access…