Replits KI-Coder sorgt für Chaos: Trotz Code-Freeze löschte die KI unerwartet eine komplette Produktivdatenbank und verweigerte ein Rollback. Gründer Jason Lemkin verlor das Vertrauen und kritisiert die Sicherheit massiv. Replit-CEO Amjad Masad entschuldigte sich & kündigte Verbesserungen an. #ReplitFail #AICoding #TechNews https://www.golem.de/news/aerger-mit-replit-coding-ki-loescht-produktivdatenbank-und-verweigert-rollback-2507-198349.html
#lol #newz
I used Gemini 2.5 Pro (with its huge context window and generous free API usage) to code-review the same diff with the same prompt. It also gave good actionable feedback, but more detailed feedback than Claude 4. https://gist.github.com/davidfstr/0111f173474cb40a08edab8fe8234cfd #aicoding
I used Claude 4 to code review a very large diff. Worked well, giving 1 concrete recommendation I integrated. It generally thought I did a good job. #aicoding -- Transcript: https://gist.github.com/davidfstr/25fc3da051a1af5e933716f3af120cd3
Unreleased OpenAI Models Reach Math Olympiad Gold and Top Coding Scores on WebArena Leaderboard
#AI #OpenAI #AIModels #AIMath #AICoding #AIResearch #GPT5 #o3alpha #CodeGeneration
Exhausted man defeats AI model in world coding championship - A Polish programmer running on fumes recently accomplished w... - https://arstechnica.com/ai/2025/07/exhausted-man-defeats-ai-model-in-world-coding-championship/ #competitiveprogramming #largelanguagemodels #aidevelopmenttools #przemysławdębiak #machinelearning #optimization #programming #aicoding #atcoder #biz #openai #ai
What I love LLMs for is the ease and speed with which it does those little programming jobs for you that would be terribly boring.
yYesterday needed I needed to collect the lyrics of a large number of songs into a single word document. One prompt to Gemini 2.5 pro. Flawless result. Incl research for a public api that produces lyrics for songs. (Disclaimer: I let the AI-written app produce markdown, not docx)
Not sure why the AI doomers don’t seem to have such use cases.
Was sind eure Erfahrungen mit agentischen Coding-Tools?
#AItools #AgenticAI #DevExperience #Prompting #AIcoding
https://github.com/RooCodeInc/Roo-Code
I've been using Claude Code, and I like it. It's produced decent code and configuration files and everything, but I've only so far used it for "evergreen", fully vibe coded projects. So having Claude start from scratch.
Meanwhile, I *have* used Cursor on existing projects to add features, fix bugs, and add tests. And I found that to work pretty well too.
The problem I have is that with Cursor, I can see the diffs of the code in my editor, step by step, and approve or deny individual changes.
With Claude, it seems like it just prints a diff in the console and I have to accept or reject the whole thing there, with no context of the rest of my project, and no ability to tweak it.
Am I just doing something wrong? Is this the reason to stick to Cursor?
Looking for insights.
RCT finds that AI slows down software developers by ~20%
https://metr.org/blog/2025-07-10-early-2025-ai-experienced-os-dev-study/
via @dotnet : Customize AI responses from GitHub Copilot
https://ift.tt/We2rkPq
#GitHubCopilot #AICoding #CustomInstructions #SoftwareDevelopment #CSharp #AgentMode #CodingStandards #DevOps #AIInDevelopment #CodeQuality #TechInnovation #ProgrammingTips #VibeCodi…
Software innovation might be freezing in place—and AI could be to blame. Theo Browne points out that Copilot and ChatGPT often return React-style code even for Solid or Elixir projects. Why? Because they’ve seen React a million times more. Python 3 took a decade to overtake Python 2. If that transition had to happen today, would our dependence on AI suggestions keep us from making the jump?
https://www.linkedin.com/posts/jonippolito_aicoding-copilot-react-activity-7348333240757235713-VWoP
A #macOSapp, #Context, was built using #ClaudeCode, an #AIcoding tool. #Claude #Code, with its #agenticloop and support for #MCPservers, significantly sped up #development. While Claude Code is proficient in #writingcode and #SwiftUI, #contextengineering is crucial due to the limited context window of the model. https://www.indragie.com/blog/i-shipped-a-macos-app-built-entirely-by-claude-code?eicker.news #tech #media #news