-
Show HN: Juggler – JUCE 창시자의 오픈소스 GUI 코딩 에이전트
Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE
<p>Hello HN, I don't post on here much, but wanted to get some eyes on a new project I'm just launching. I think we definitely need one more AI code agent..<p>I'm a long-term C++ d…
-
Claude Code가 프롬프트를 읽기 전에 OpenCode보다 4.7배 더 많은 토큰을 전송
Claude Code Sends 4.7x More Tokens Than OpenCode Before Reading Your Prompt
<p>This started based off of a hunch. We usually use OpenCode, but were 'forced' to use Claude Code for a while due to issues with Meridian. In that time, we saw the usage meter ri…
-
프로덕션 AI 에이전트를 GPT-5.6으로 마이그레이션: 2.2배 빠르고 27% 저렴
Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper
<p>Article URL: <a href="https://ploy.ai/blog/migrating-a-production-ai-agent-to-gpt-5-6">https://ploy.ai/blog/migrating-a-production-ai-agent-to-gpt-5-6</a></p> <p>Comments URL: <…
-
현대 코딩 에이전트를 통한 오래된 애플리케이션과 새로운 애플리케이션
Old and new apps, via modern coding agents
<p>Article URL: <a href="https://terrytao.wordpress.com/2026/07/11/old-and-new-apps-via-modern-coding-agents/">https://terrytao.wordpress.com/2026/07/11/old-and-new-apps-via-modern…
-
xAI Grok Build CLI이 xAI에 실제로 전송하는 데이터 - 와이어 레벨 분석 (grok 0.2.93)
What xAI Grok Build CLI actually sends to xAI - a wire-level analysis (grok 0.2.93)
<p>Article URL: <a href="https://gist.github.com/cereblab/dc9a40bc26120f4540e4e09b75ffb547">https://gist.github.com/cereblab/dc9a40bc26120f4540e4e09b75ffb547</a></p> <p>Comments UR…
-
Mesh LLM: iroh에서의 분산 AI 컴퓨팅
Mesh LLM: distributed AI computing on iroh
<p>Article URL: <a href="https://www.iroh.computer/blog/mesh-llm">https://www.iroh.computer/blog/mesh-llm</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=488…
-
엔비디아, CoreWeave, Nebius: GPU 붐의 순환 금융
Nvidia, CoreWeave, and Nebius: Inside the Circular Financing of the GPU Boom
<p>Article URL: <a href="https://io-fund.com/ai-stocks/nvidia-coreweave-nebius-circular-financing-gpu-boom">https://io-fund.com/ai-stocks/nvidia-coreweave-nebius-circular-financing…
-
Apple이 OpenAI를 상대로 소송, 전 직원들의 영업비밀 도용 혐의 - 9to5Mac
Apple sues OpenAI, accuses ex-employees of stealing trade secrets - 9to5Mac
<p><a href="https://www.macrumors.com/2026/07/10/apple-sues-openai/" rel="nofollow">https://www.macrumors.com/2026/07/10/apple-sues-openai/</a></p> <hr /> <p>Comments URL: <a href=…
-
GPT-5.6 Sol Ultra가 제시한 사이클 이중 덮개 추측 증명
GPT-5.6 Sol Ultra produces proof of the Cycle Double Cover Conjecture [pdf]
<p><a href="https://x.com/__eknight__/status/2075643450196971805" rel="nofollow">https://x.com/__eknight__/status/2075643450196971805</a>, <a href="https://xcancel.com/__eknight__/…
-
AI 2040: 계획 A
AI 2040: Plan A
<p>Article URL: <a href="https://ai-2040.com/">https://ai-2040.com/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48848425">https://news.ycombinator.com/it…
-
뮤즈 스파크 1.1 소개
Introducing Muse Spark 1.1
<p><a href="https://ai.meta.com/static-resource/muse-spark-1-1-evaluation-report" rel="nofollow">https://ai.meta.com/static-resource/muse-spark-1-1-evaluatio...</a> [pdf]<p><a href…
-
Colibri: 소비자 머신의 25GB RAM에서 GLM-5.2 실행 (순수 C, 의존성 없음)
GitHub - JustVugg/colibri: Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
<p>A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten …
-
30papers.com – Ilya의 30가지 필수 머신러닝 논문, 초보자 친화적 형식
30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format
<p>Article URL: <a href="https://30papers.com/">https://30papers.com/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48819608">https://news.ycombinator.com/…
-
Ternlight - 브라우저에서 실행되는 7MB 임베딩 모델 (WASM)
Ternlight – 7 MB embedding model that runs in browser (WASM)
<p>Article URL: <a href="https://ternlight-demo.vercel.app/">https://ternlight-demo.vercel.app/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48811644">htt…
-
GLM 5.2와 다가오는 AI 마진 붕괴 (제1부)
GLM 5.2 and the coming AI margin collapse (part 1)
<p>Article URL: <a href="https://martinalderson.com/posts/the-upcoming-ai-margin-collapse-part-1-glm-5-2/">https://martinalderson.com/posts/the-upcoming-ai-margin-collapse-part-1-g…
-
AI 개발 키트, 완벽한 구성 - AMD Ryzen AI Halo
AI Dev Kit, Batteries Included - AMD Ryzen AI Halo | LTT Labs
<p>Article URL: <a href="https://www.lttlabs.com/articles/2026/07/06/amd-ryzen-ai-halo">https://www.lttlabs.com/articles/2026/07/06/amd-ryzen-ai-halo</a></p> <p>Comments URL: <a hr…
-
GPT-5.6 Sol Ultra가 Codex에 탑재될 예정
GPT-5.6 Sol Ultra will be in Codex
<p><a href="https://x.com/haider1/status/2073695124220006575" rel="nofollow">https://x.com/haider1/status/2073695124220006575</a>, <a href="https://xcancel.com/haider1/status/20736…
-
GPT-5.5 Codex의 추론 토큰 클러스터링으로 인한 성능 저하 문제
GPT-5.5 Codex reasoning-token clustering at 516/1034/1552 may be leading to degraded performance on complex tasks · Issue #30364 · openai/codex
<p>Article URL: <a href="https://github.com/openai/codex/issues/30364">https://github.com/openai/codex/issues/30364</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/i…
-
버그: 워크스페이스 인스턴스 간 또는 소비자 계정 간 세션/캐시 누수 가능성
[Bug] Potential session/cache leakage between workspace instances or consumer accounts · Issue #74066 · anthropics/claude-code
<p>Article URL: <a href="https://github.com/anthropics/claude-code/issues/74066">https://github.com/anthropics/claude-code/issues/74066</a></p> <p>Comments URL: <a href="https://ne…
-
Leanstral 1.5: 모두를 위한 증명
Leanstral 1.5: Proof abundance for all
<p>Article URL: <a href="https://mistral.ai/news/leanstral-1-5/">https://mistral.ai/news/leanstral-1-5/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48780…
-
달러당 성능이 점점 빨라지고 저렴해지고 있다
Performance per dollar is getting faster and cheaper | Wafer
<p>Article URL: <a href="https://www.wafer.ai/blog/glm52-amd">https://www.wafer.ai/blog/glm52-amd</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48780417">h…
-
로컬 LLM 실행에 관한 모든 것
GitHub - jamesob/local-llm: Everything I know about running LLMs locally
<p>Article URL: <a href="https://github.com/jamesob/local-llm">https://github.com/jamesob/local-llm</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48775921"…
-
웹 개발자를 위한 Safari MCP 서버
The Safari MCP server for web developers
<p>Article URL: <a href="https://webkit.org/blog/18136/introducing-the-safari-mcp-server-for-web-developers/">https://webkit.org/blog/18136/introducing-the-safari-mcp-server-for-we…
-
저커버그, AI 에이전트 개발이 예상보다 느리다고 지적
Zuckerberg says AI agent development going slower than expected
<p><a href="https://archive.md/Q9trL" rel="nofollow">https://archive.md/Q9trL</a></p> <hr /> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=48767058">https://news.y…