Install
A constructive and inclusive social network for software developers. With you every step of your journey.
- 108,783articles · 365d
- 1+ hour agolatest article
- Sep 13, 2025earliest in window
- 95%with images
- 292avg words
- software 96,115
- coding 91,899
- development 91,771
- engineering 91,336
- community 90,726
- inclusive 90,554
- ai 65,787
- webdev 56,796
- programming 54,506
- artificial intelligence 32,310
- technology 28,245
- productivity 26,464
- beginners 24,639
- javascript 21,929
- devops 20,454
- tutorial 20,125
- security 18,196
- python 17,848
- architecture 12,698
- llm 9,904
- Science & Technology 91,368
- Software Dev. 90,289
- Computers & Electronics 70,946
- Business & Industrial 9,241
- Arts, Culture, Entertainment & Media 7,842
- Internet & Telecom 7,151
- Economy, Business & Finance 5,215
- Arts & Entertainment 3,770
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
🔁 Pendant un hackathon data... je trouve une opportunité de CDO dans ma propre entreprise 😹
35+ min ago (22+ words) ❔Contexte Le #HackAVP - le premier hackathon dédié aux AVPs de l'OPT-NC - a été lancé... Tagged with career, hackavp, hackathon, ai....
Two "Codex CLI" models on the same benchmark: the harness hides the model
26+ min ago (260+ words) Specific Labs dropped Real-SWE, an enterprise-code SWE benchmark, and the leaderboard is a great study in why you should never read "Claude Code" or "Codex CLI" as a model name. Same harness, two different brains: Same vendor's CLI, same harness,…...
Giving a coding agent more time barely helps
26+ min ago (627+ words) Real-SWE ran frontier models against licensed, private enterprise codebases (billing, tax, multi-service work) and one number jumped out at me: rollout duration barely moves resolution. 71.4% of rollouts that finished in under 10 minutes FAILED. 73.4% of rollouts that ran 10 minutes or longer…...
Why the New LLM Reasoning Leak Paper Matters for Your Team’s AI Workflow
40+ min ago (271+ words) The technique works in just two API calls and can recover reasoning that was meant to stay hidden behind the provider’s safety layers. The authors demonstrate this with several examples, including a case they call Kimi‑K3 where the recovered reasoning…...
My Scanner Passed Until I Built a Harness That Lied to It on Purpose
40+ min ago (271+ words) Every security tool has a dirty secret: nobody tests whether the detector detects. The tests pass, the CI is green, and everyone moves on. Today I pointed my own scanner, mcpscan, at a set of synthetic attack files I wrote…...
Agent-Cache: Multi-Tier LLM Caching for Valkey and Redis
29+ min ago (666+ words) Agent loops burn tokens and clock cycles on repeated work. The same LLM prompt fires twice, the same tool call fetches identical data, and session state gets reconstructed from scratch on every request. Agent-cache solves this with a three-tier caching…...
No Server, No Backend, Just Blazor WebAssembly Doing Semantic Search
46+ min ago (1050+ words) 🚀 Semantic search on GitHub Pages with zero backend I recently added semantic search to... Tagged with blazor, webdev, embedding, dotnet....
ทำไม KV cache ถึงกลายเป็นหัวใจเศรษฐศาสตร์ของ AI agent ในปี 2026
1+ hour, 10+ min ago (125+ words) โดย Nokka (นก-กา) | 13 กันยายน 2026 หัวใจคือชื่อ Causal Encoder-Decoder หรือ CED [1] ทั้งที่ backbone ทั้งหมดมี 552B พารามิเตอร์ [1] และมี FP4 KV caching ในฟอร์แมต E2M1 โดยใช้สเกลหนึ่งตัวต่อ 16 แชนเนล [1] รวมกันแล้ว KV cache ทั้งหมดเหลือ…...
My Extraction Score Was 0.08 and the Model Was Innocent: Rebuilding the Ruler
1+ hour, 27+ min ago (745+ words) CauterRule is an open-source sidecar that learns standing rules from repeated agent failures. It extracts lessons from trajectories, replay-tests them, and tries to separate reusable guidance from noisy overgeneralization. The last article ended on an open question: at what point…...
Implementing a Secure MCP Server
1+ hour, 41+ min ago (910+ words) An MCP server often starts with a seemingly simple requirement: an AI host should find and summarise... Tagged with ai, mcp, architecture, gemma....