ai-assisted

Tag

Cards List
#ai-assisted

Show HN: Reviving my 2001 college band with AI

Hacker News Top ↗ · 2026-07-09 Cached

A former college band, Fading Maize, revives its 2001 recordings using AI-assisted production, design, and video, with original archives preserved alongside new versions.

0 favorites 0 likes
#ai-assisted

@2prime_PKU: We just used AI to solve a 35-year-old open math problem! In queuing theory, BAR is the "master equation" for finding n…

X AI KOLs Timeline ↗ · 2026-07-07 Cached

Researchers used AI, specifically ChatGPT 5.5 Pro, to solve the 35-year-old Signed BAR Conjecture in queuing theory, proving uniqueness of stationary distributions for reflected diffusions. The result advances understanding of equilibrium in stochastic networks and demonstrates AI's role in mathematical discovery.

0 favorites 0 likes
#ai-assisted

@Vinkyu567: https://x.com/Vinkyu567/status/2073399058535002336

X AI KOLs Timeline ↗ · 2026-07-04 Cached

This tutorial shows how to build a local and cloud-synced AI knowledge base in 5 minutes using Obsidian, Markdown, GitHub, and AI assistance (Codex), and recommends related plugins.

0 favorites 0 likes
#ai-assisted

Waveloop: What Fable left me

Hacker News Top ↗ · 2026-06-26 Cached

The author recounts using the AI model Fable 5 to create Waveloop, a music visualizer that reveals harmonic and melodic structure through a chromatic circle. It uses color and angle to represent pitch classes and intervals, with offline and live mic modes.

0 favorites 0 likes
#ai-assisted

Show HN: Turn native language audio into flashcards and shadowing practice

Hacker News Top ↗ · 2026-06-25

LingoChunk is a tool that converts native language audio into Anki flashcards and shadowing practice, supporting 15 input languages and over 30 output languages.

0 favorites 0 likes
#ai-assisted

@nini_incrypto_: Recommended Paper Writing Skills 1 Research-Paper-Writing-Skills https://github.com/Master-cai/Research-Paper-Writing-Skills… This is a skill pack for machine learning/computing...

X AI KOLs Timeline ↗ · 2026-06-24 Cached

Recommends four open-source paper writing skill packs suitable for machine learning/computer vision/NLP and other fields, focusing on structure standardization, polishing and review, complete research workflow, and Chinese collaboration, supporting AI assistants such as Codex, Claude Code, and Gemini.

0 favorites 0 likes
#ai-assisted

Shipping huggingface_hub every week with AI, open tools, and a human in the loop

Hugging Face Blog ↗ · 2026-06-23 Cached

Hugging Face describes how they built a weekly release pipeline for their huggingface_hub library using AI, open-source tools, and human oversight, enabling faster and more reliable releases.

0 favorites 0 likes
#ai-assisted

@VincentLogic: The hardest part of reading someone else’s code isn’t that you can’t understand a single line. It’s that you have no idea where you are. When you open a unfamiliar repo, files, calls, services, and dependencies are all mixed together, and AI explanations often just read through the files verbatim. The Understand-Anything approach is quite aggressive: it directly turns the codebase into a…

X AI KOLs Timeline ↗ · 2026-06-22 Cached

Introduces the Understand-Anything tool, which transforms a codebase into a clickable, searchable, call-tracking knowledge graph to help developers understand unfamiliar projects.

0 favorites 0 likes
#ai-assisted

Patch the Planet: a Daybreak initiative to support open source maintainers

OpenAI Blog ↗ · 2026-06-22 Cached

OpenAI announces Patch the Planet, an initiative with Trail of Bits to help open-source maintainers strengthen security by using AI models to identify and patch vulnerabilities, reducing the burden on maintainers.

0 favorites 0 likes
#ai-assisted

@AnthropicAI: Domain experts—as judged by the questions they ask and vocabulary they use about a subject—are more likely to see succe…

X AI KOLs ↗ · 2026-06-16 Cached

Anthropic shares that domain experts show higher success in coding, but the gap between intermediate and expert users is modest, suggesting domain proficiency is sufficient.

0 favorites 0 likes
#ai-assisted

@mattpocockuk: Here are my 7 phases of AI-powered development. I've been thinking that the pre-PRD phase needs more structure. You nee…

X AI KOLs Following ↗ · 2026-06-15 Cached

Matt Pocock shares his seven phases of AI-powered development, emphasizing the need for more structure in the pre-PRD phase.

0 favorites 0 likes
#ai-assisted

@qkl2058: A girl single-handedly tanked the stock prices of Figma and Photoshop. She created a new technique called "touchdesign" and made $420,000 from it. The technique has been used in Nolan's new film 'The Odyssey'. The idea was hers; Claude helped her build it from scratch. I took this...

X AI KOLs Timeline ↗ · 2026-06-10 Cached

A girl used Claude AI and free software TouchDesigner and MediaPipe to develop a real-time interactive system for controlling 3D objects with hand gestures at extremely low cost, and successfully commercialized it, charging $5,000–$15,000 per event.

0 favorites 0 likes
#ai-assisted

Porting the ThinkPad X61 to Coreboot

Hacker News Top ↗ · 2026-06-09 Cached

A blog post detailing the process of porting the ThinkPad X61 to the coreboot open-source firmware, using AI-assisted reverse engineering with Claude Opus 4.6.

0 favorites 0 likes
#ai-assisted

@PrajwalTomar_: Lovable has CLAUDE .md now. It's called Skills. Write your project rules once. Lovable reads them on every build foreve…

X AI KOLs Following ↗ · 2026-06-08 Cached

Lovable introduces Skills, a feature similar to CLAUDE .md that allows developers to define persistent project rules (e.g., brand voice, stack conventions) that Lovable reads on every build, improving output consistency.

0 favorites 0 likes
#ai-assisted

FVSpec: Real-World Property-Based Tests as Lean Challenges

Hugging Face Daily Papers ↗ · 2026-05-31 Cached

This paper presents FVSpec, a benchmark for AI-assisted formal verification that translates real-world property-based tests from Python into Lean 4 specifications using a multi-agent LLM pipeline, aiming to drive progress on formal verification of real-world software.

0 favorites 0 likes
#ai-assisted

The pressure

Simon Willison's Blog ↗ · 2026-05-26 Cached

Daniel Stenberg describes the unprecedented pressure on the curl project due to a deluge of credible AI-assisted security reports, which have quadrupled the rate of incoming reports and increased the workload, while noting that most vulnerabilities found are low or medium severity.

0 favorites 0 likes
#ai-assisted

@SethSHowes: I just sequenced a human genome to 30× coverage entirely at home. As far as I know, this is the first time this has bee…

X AI KOLs Following ↗ · 2026-05-25 Cached

A researcher sequenced a human genome to 30× coverage entirely at home using an Oxford Nanopore P2 Solo, marking the first time this has been done outside a lab. He attributed his success to AI helping solve technical problems across software, hardware, and molecular biology.

0 favorites 0 likes
#ai-assisted

Mad House — Usborne Creepy Computer Games

Simon Willison's Blog ↗ · 2026-05-24 Cached

A developer used Claude to recreate the 'Mad House' game from a 1980s Usborne book as an interactive JavaScript artifact, complete with retro aesthetic and mobile-friendly design.

0 favorites 0 likes
#ai-assisted

@binbinmath: https://x.com/binbinmath/status/2058039550551724201

X AI KOLs Timeline ↗ · 2026-05-23 Cached

The founder used AI assistance to create a complete knowledge base website mungermodels.com for Charlie Munger's 232 mental models, containing 1.52 million words of detailed analysis and 1,915 bidirectional links, completely free and open.

0 favorites 0 likes
#ai-assisted

@BenjaminDEKR: AI-assisted CAD is entering its "vibe code" arc. It's right on the edge of being world-changingly good. Anyone who can …

X AI KOLs Following ↗ · 2026-05-22 Cached

AI-assisted CAD is on the verge of a breakthrough, enabling anyone to describe physical objects and see them designed instantly, with potential for on-demand parts and assembly.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback