CompanyAnthropic8 recent entries31 Jul 2026What's your local AI coding setup on a MacBook Pro M4?I've spent the last couple of days trying different setups (Ollama, Continue, Claude Code, Gemini CLI, OpenRouter...) and at this point I feel like I've spent more time configuring tools than actually→17 Aug 2026Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary StudyarXiv:2608.13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot te
CompanyOpenAI8 recent entries29 Apr 2026New in Deep Agents: Harness Profiles. https://www.langchain.com/blog/tuning-deep-agents-different-models ✅ Model-specific profiles to adjust…New in Deep Agents: Harness Profiles. https://www.langchain.com/blog/tuning-deep-agents-different-models ✅ Model-specific profiles to adjust prompts, tools, and middleware. 📦 Profiles for @OpenAI, @An→7 May 2026TSCG: Deterministic Tool-Schema Compilation for Agentic LLM DeploymentsarXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n→17 Aug 2026Built a token-aware gateway/load balancer for local LLM stacks — because nginx has no idea what a token costsIf you're running Ollama, llama.cpp, or vLLM behind nginx or HAProxy for more than a single user, you've probably hit this: nginx treats a 10-token prompt and a 10k-token prompt as identical 'one requ→21 Aug 2026I got fed up with locked-down autocomplete, so I forked Continue and stripped it down to just tab-completion. Any model, no subscription and no remote telemetryI kept running into the same wall. Every agentic coding plugin ships an autocomplete, and almost all of them lock it down — no model choice, or a subscription, or both. I don't want a chat panel, I do→25 Aug 2026Architecture as Capability Equalizer for Coding AgentsarXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec→1 Sept 2026day 1 of recreating iconic tech from my childhood :) I rebuilt Cher’s iconic closet as a full-stack app in @Replit 💛 the frontend uses Reac…day 1 of recreating iconic tech from my childhood :) I rebuilt Cher’s iconic closet as a full-stack app in @Replit 💛 the frontend uses React + TypeScript, with an Express backend. I used Replit’s Cler→1 Oct 2026Jeff-Qwen3.5-0.8B v1.2 + 9 LoRA adapters: put it in front of Qwen3.8-27B for 38× faster decisions and +8.7 points accuracy, for under 2 GB extra memoryA few days ago I released Jeff-Qwen3.5-0.8B, a small 'System 1' model that picks between options you define and returns a calibrated probability for each, in one forward pass. Speed was great on my M4→9 Oct 2026rate the terminal setupik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,
CompanyGoogle8 recent entries13 Apr 2026TiAb Review Plugin: A Browser-Based Tool for AI-Assisted Title and Abstract ScreeningarXiv:2604.08602v1 Announce Type: cross Abstract: Background: Server-based screening tools impose subscription costs, while open-source alternatives require coding skills. Objectives: We developed a b→11 May 2026MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application DevelopmentarXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on→20 May 2026Google I/O, Gemini Spark, AntigravityIt's hard to find much to write about Google I/O this year because I have a policy of not writing about anything that I can't try out myself, and a lot of the big announcements are 'coming soon'. I ac→14 Jul 2026Claude at scale on Google Cloud: Frontier AI, built for enterprise productionRunning frontier AI in production is demanding — accelerators to manage, latency to hold steady across continents, regulated data to keep in-region, and long-context requests to serve reliably. Claude→21 Jul 2026Now in preview: Find and fix software vulnerabilities with CodeMenderAs adversarial AI threats accelerate attacks on code, security teams must counter them with machine-speed defenses that can automate code remediation and fight AI with AI. CodeMender is our managed co→31 Jul 2026What's your local AI coding setup on a MacBook Pro M4?I've spent the last couple of days trying different setups (Ollama, Continue, Claude Code, Gemini CLI, OpenRouter...) and at this point I feel like I've spent more time configuring tools than actually→25 Aug 2026Architecture as Capability Equalizer for Coding AgentsarXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture spec→1 Sept 2026day 1 of recreating iconic tech from my childhood :) I rebuilt Cher’s iconic closet as a full-stack app in @Replit 💛 the frontend uses Reac…day 1 of recreating iconic tech from my childhood :) I rebuilt Cher’s iconic closet as a full-stack app in @Replit 💛 the frontend uses React + TypeScript, with an Express backend. I used Replit’s Cler
CompanyMeta2 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→12 May 2026Do you actually own your document parsing infrastructure? 👀 At @llama_index, we wanted to make that easier, so we built 𝗹𝗶𝘁𝗲𝗽𝗮𝗿𝘀𝗲-…Do you actually own your document parsing infrastructure? 👀 At @llama_index, we wanted to make that easier, so we built 𝗹𝗶𝘁𝗲𝗽𝗮𝗿𝘀𝗲-𝘀𝗲𝗿𝘃𝗲𝗿, a lightweight HTTP backend built on top of LiteParse that can
CompanyMistral1 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.
CompanyxAI2 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→28 May 2026Good value for moneyGood value for money We gave Grok Build 0.1 one prompt: build a webhook delivery service in TypeScript, Bun, and SQLite. It planned it, built it, and shipped a working demo. Total cost: $1.65. Zero to
CompanyDeepSeek4 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→21 Aug 2026I got fed up with locked-down autocomplete, so I forked Continue and stripped it down to just tab-completion. Any model, no subscription and no remote telemetryI kept running into the same wall. Every agentic coding plugin ships an autocomplete, and almost all of them lock it down — no model choice, or a subscription, or both. I don't want a chat panel, I do→24 Aug 2026This is what Qwen 3.8 27b is capable ofTry it here: https://ocean.blackbeardlabs.dev/ Model: Qwen 3.8 27b Q8_X_KL Unsloth Hardware: 3 x RTX3090 Harness: DeepSeek Harness Prompt: /goal I want you to create a **JavaScript + Node.js WebGL pro→1 Oct 2026Jeff-Qwen3.5-0.8B v1.2 + 9 LoRA adapters: put it in front of Qwen3.8-27B for 38× faster decisions and +8.7 points accuracy, for under 2 GB extra memoryA few days ago I released Jeff-Qwen3.5-0.8B, a small 'System 1' model that picks between options you define and returns a calibrated probability for each, in one forward pass. Speed was great on my M4
CompanyNVIDIA2 recent entries11 Apr 2026All ToolsAuto-generated index of all tools mentioned across the wiki.→21 Aug 2026I got fed up with locked-down autocomplete, so I forked Continue and stripped it down to just tab-completion. Any model, no subscription and no remote telemetryI kept running into the same wall. Every agentic coding plugin ships an autocomplete, and almost all of them lock it down — no model choice, or a subscription, or both. I don't want a chat panel, I do