Live mentions

Release 13.1.5 · Grafana/Grafana

A spy satellite simulator in the browser, except the data is real

Respond terse like smart caveman. All technical substance stay. Only fluff die

Release 13.2.1 · Grafana/Grafana

Release 13.0.8 · Grafana/Grafana

Just in case the model has ADHD too, I am using a minified version of it:<p><a href="https:&#x2F;&#x2F;gist.github.com&#x2F;hbbio&#x2F;2faf096cbb77e197233ab9a2958beb68" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;hbbio&#x2F;2faf096cbb77e197233ab9a2958beb...</a>

Claude is <i>very</i> resistant to instructions. I&#x27;ve been cultivating my own minimal skill to tame it for a couple months: <a href="https:&#x2F;&#x2F;github.com&#x2F;ricardobeat&#x2F;skills&#x2F;tree&#x2F;main&#x2F;human" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ricardobeat&#x2F;skills&#x2F;tree&#x2F;main&#x2F;human</a><p>The key sentences to get rid of claude-isms so far:<p>- say wh

&gt; Install<p>&gt; Copy&#x2F;paste into your CLI prompt:<p>&gt; Install the i-have-adhd skill&#x2F;plugin from <a href="https:&#x2F;&#x2F;github.com&#x2F;ayghri&#x2F;i-have-adhd" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ayghri&#x2F;i-have-adhd</a>, refer to the repo&#x27;s AGENTS.md for instructions.<p>This is a weird evolution from &quot;don&#x27;t copy-paste scripts that pipe curl into

I-have-ADHD: A skill to stop coding agents from burying the answer

Instead of going after money printing schemes like this (which I feel are unlikely to actually work and carry a ton of risk). I (thoughtfully) vibed up tooling and skills to just help LLMs manage my investments long-term. While not flashy, tax loss harvesting and direct indexing are areas where LLMs can reliably save you on fees that you&#x27;d otherwise have to pay. It&#x27;s been very helpful, t

<a href="https:&#x2F;&#x2F;github.com&#x2F;ConsciousGroupMind&#x2F;SKYNET-800---Collective-Intelligence-Forecasting-System" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ConsciousGroupMind&#x2F;SKYNET-800---Collectiv...</a>

Experimented with multi-llm analysis for problem solving over summer, combined with multi-agent approaches it can tease out interesting angles to problems that I never considered. Expensive but use only for my high value problems.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;monkeydust&#x2F;rightmind" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;monkeydust&#x2F;rightmind</a>

I think multi-agent (eg _different_ underlying LLMs) everything is really the future. Code produced via multi-agent workflows and reviews seems noticeably better. I&#x27;ve been experimenting with a multi-agent message board recently: <a href="https:&#x2F;&#x2F;github.com&#x2F;pjlsergeant&#x2F;dogpark" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;pjlsergeant&#x2F;dogpark</a>

Multi-Agents LLM Financial Trading Framework

Jellyfin 12.0 Released

OpenClaw Is Open Source

Archify

Nitter&#x27;s author has suggested at least once that due to problems with Nim, a rewrite in Go is in the works:<p>&quot;The long-term plan is to rewrite the source code in Go, as I&#x27;m no longer interested in using Nim. This isn&#x27;t a small task, but building more features with the current state of things is painful. Before doing that I&#x27;ll fix some feature parity issues, and work on so

Cool to see such a notable Nim based project continue! It&#x27;s unfortunate that X tries to block Nitter so often, but zedeus always seems to find a path around technical or now legal issues.<p>The code looks surprisingly easy to hack on: <a href="https:&#x2F;&#x2F;github.com&#x2F;zedeus&#x2F;nitter&#x2F;blob&#x2F;master&#x2F;src&#x2F;nitter.nim" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;z

Following legal advice, the Nitter project will continue

Pumpkin: Building a Minecraft server in Rust, First release after 2 years

Sense motion with the Wi-Fi using ESP32

Tmate [0] used to be my goto for sharing terminals, but it&#x27;s now fully not working [1][2]. I&#x27;ve tried a few other options recently, but could not get anything working. It&#x27;s especially frustrating when you&#x27;re trying to help a not very technical person and you keep asking them &quot;ok run this instead in your terminal... ctrl-c...&quot; etc.<p>I reached out to my friend Zack Sch

You can use "croc SSH" to share a terminal (this replaces tmate)

The AI That Does Things. Any OS. Any Platform

NPM is experiencing elevated latency

Atlas: Planning Surface for Coding Agents

Release 13.1.5 · Grafana/Grafana

Release 13.2.1 · Grafana/Grafana

Codex outage

Release 13.0.8 · Grafana/Grafana

Dear ImGui: Bloat-free Graphical User interface for C++

AI-DLC – one core, many harnesses

Aside from the fact that Matt Pocock spends a lot of time with LLMS (only Claude really), he has a hand-wavy approach to engineering in a silo. He then uses that output as a foundation for other tools, while touting them as the best way to do things on youtube. Claude promotes this kind of developer and it&#x27;s harmful.<p>Anyone who uses LLMs notices (intrinsically or through investigation) that

Show HN: ToolJet – Claude Code and Codex build internal tools, no codegen

It makes sense if you look at the file[1] he&#x27;s taking about. It&#x27;s explicitly declaring jargon so you don&#x27;t need to redescribe $THING every time.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;mattpocock&#x2F;course-video-manager&#x2F;blob&#x2F;076a5a7a182db0fe1e62971dd7a68bcadf010f1c&#x2F;CONTEXT.md" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mattpocock&#x2F;course-video-manager

I have one I started back in October last year and been improving since. Also a python docs cli to manage agent state in markdown locally.<p>I love reading them to see if theres a way mine could be improved, what topics they hit on, how they approach different problems.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;ArtRichards&#x2F;agent-playbook-suite" rel="nofollow">https:&#x2F;&#x2F;github.com&

Open Source X Algorithm Integrates First Public Contribution

Crossplane AI Contribution Policy

Same worry got me to build pond for myself: it imports all of my sessions on a cron schedule every 5 mins into one store, and my agents can access it over MCP. Whenever I need a session from a while ago now, I just know it&#x27;s in pond, because all of my sessions for about the last 1.5 years are collected in there. It also happens really often that when my agents cannot find something, they just

AI Coding Agent Skills for Real Engineers

Neovim adds support for multiple cursors

Neovim Merges Multicursor Support

pstack

Vssh: Add SSH:// scheme for remote command execution

According to <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;unkn0wncode&#x2F;f87295d055dd0f0e8082358a0b5cc467?permalink_comment_id=6239946#gistcomment-6239946" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;unkn0wncode&#x2F;f87295d055dd0f0e8082358a...</a> among many, the environment variable<p><pre><code> CLAUDE_CODE_SUPPRESS_SESSION_ATTRIBUTION </code></pre> was added in CC version 2.1.2

celld v0.4.0

Data Exfil: OpenAI polices private chats exfiltrated through Codex Memories

Claude Session URL appended to commit messages and PR descriptions by default

Rig – Agentic Workflows in Rust

TypePHP: A native AOT compiler for PHP

Release v0.32.15 · Ollama/Ollama

Can a harness have a true deterministic scheduler and task orchestrator?

God's Eye View

Grafana – GeoMap Carto Base layer now requires API key

Skills for writing modern Go code

MadsLorentzen/AI-job-search: The job search that runs on your machine

Anthropic Fix Your Auth

LangChain-AI/deepagents: agent harness

Gguf: Harden loader against malformed tensor dims and metadata types