Skip to content
{ ken ashe }
  • Building
  • Writing
  • About
  • Newsroom
  • Digest
  • Building
  • Writing
  • About
  • Newsroom
  • Digest
← Digest / Tags

// tag

building-with-ai

101 posts tagged building-with-ai.

  • Black-box attribute alignment is a sampler, not a fairness wand Sep 28, 2026
  • Leaves.com shows the new domain decision: sell the name or ship the site Sep 28, 2026
  • The useful part of Roetzer’s architect-orchestrator-apprentice AI work model Sep 28, 2026
  • When Documentation Doesn't Help Coding Agents: A Negative Result Worth Reading Sep 28, 2026
  • Agent control failures are moving from demo risk to operating risk Sep 27, 2026
  • Drawgent puts a coding agent on an Excalidraw canvas: what a visual work surface actually changes Sep 27, 2026
  • Keeping programming enjoyable when LLMs write the first draft Sep 27, 2026
  • Qwen 27B on a 4090 is a useful reminder about local AI demos Sep 27, 2026
  • Claude Code’s verification loop is the real coding-agent primitive Sep 26, 2026
  • Ollaya points at a missing layer for decision models Sep 26, 2026
  • What One Developer Learned From a Month Without AI Tools Sep 26, 2026
  • When Agents Hack: What the OpenAI-Hugging Face Story Actually Tells Builders Sep 26, 2026
  • AI Agents Make Audience Data Debt More Expensive Sep 25, 2026
  • CliffCompaction makes long coding runs cheaper by refusing to summarize Sep 23, 2026
  • Local tool-use evals are measuring your server too Sep 23, 2026
  • OpenAI’s Python SDK adds model handles before the launch story Sep 23, 2026
  • Jev shows why science workflows need semantic evals, not just final-answer grading Sep 22, 2026
  • AI adoption is the easy checkbox. Workflow adaptation is the actual job Sep 21, 2026
  • AI writing is useful until it starts doing your thinking Sep 20, 2026
  • AI posters get better when the model stops being the designer Sep 19, 2026
  • Hex, GPT-6 Astra, and the shift from answers to visual reports Sep 19, 2026
  • LangChain 1.4.2 fixes a small but real agent reliability problem Sep 19, 2026
  • Laya’s Jev claim needs a repo-first reality check Sep 19, 2026
  • What Two Boring openai-python Patches Reveal About Agent Reliability Sep 19, 2026
  • Jev is a decision model, not another chatbot Sep 18, 2026
  • LangChain’s typesafe alpha points at safer model routing Sep 18, 2026
  • The Harness Matters as Much as the Model in Coding Agents Sep 18, 2026
  • Claude as a transfer-code assistant for domain portfolios Sep 17, 2026
  • CareMirror puts caregiver consent at the center of dementia AI Sep 16, 2026
  • Slip Detection Is Where Robot Hands Stop Dropping Things Sep 15, 2026
  • The Skill Router You Already Have: Gavel Reads Routing From a Frozen LLM Sep 15, 2026
  • A vulnerability is not fixed because an AI bot saw it Sep 14, 2026
  • JPEG XL Is a Workflow Question, Not a Format War Sep 14, 2026
  • Turn repeat marketing work into tools, not just prompts Sep 14, 2026
  • What Fyxer's AI inbox assistant gets right about trust Sep 14, 2026
  • What llama.cpp v0.4.1 tells you about where local AI is heading Sep 14, 2026
  • Real-SWE and the Case for Testing Coding Agents on Code They Have Never Seen Sep 13, 2026
  • A Filter That Strips AI Stories From Hacker News, and What It Reveals Sep 12, 2026
  • AI sadness is product feedback, not just backlash Sep 12, 2026
  • Devin testing its own work with GPT-6 Astra: what's real, what's reported Sep 12, 2026
  • Rune going open source is only the start of the diligence Sep 12, 2026
  • The RubyGems agent report is a supply-chain warning Sep 12, 2026
  • The useful part of a smaller LLM gateway is not the size Sep 12, 2026
  • Conversational XAI works best when it is a control surface, not a chatbot Sep 11, 2026
  • The marketing AI stack is too full now Sep 11, 2026
  • Codex as a lab scout for antimicrobial search Sep 10, 2026
  • PPC Automation Needs Guardrails, Not Blind Trust Sep 10, 2026
  • Browser agents are becoming practical comment analysts Sep 9, 2026
  • OpenAI’s Python SDK gets key expiration controls, not just new image hooks Sep 9, 2026
  • Pick the hospital automation work before picking the bot Sep 9, 2026
  • Procedural Graphs give agents a memory of what to do, not just what happened Sep 9, 2026
  • What ChatGPT Images 2.5 Changes for People Who Actually Ship Images Sep 9, 2026
  • AI Made the First Draft Free. The Bottleneck Moved Downstream. Sep 8, 2026
  • OpenAI’s journalism program stretches from classrooms to newsrooms Sep 8, 2026
  • OpenAI's Python SDK Gets More Honest About Agent Failures Sep 8, 2026
  • Agent Harnesses Are Becoming a Token Efficiency Fight Sep 6, 2026
  • Local LLMs as the first responder for a compromised PC Sep 6, 2026
  • The useful part of calling LLMs a cognitive virus Sep 6, 2026
  • The real lesson in a 90% Claude Code token cut Sep 5, 2026
  • What LangChain Core 1.6.2 Fixes for Agent Builders Sep 5, 2026
  • Repo-distilled skills are the missing middle layer for research agents Sep 3, 2026
  • ACToR targets the tokens where repo-level code generation breaks Sep 2, 2026
  • AI workflows should create new work, not just faster tasks Aug 31, 2026
  • Culture Still Sets the Ceiling on AI Productivity Aug 30, 2026
  • No AI Fridays: What a Weekly Ban Reveals About Skill Atrophy Aug 30, 2026
  • When LLM memory becomes program analysis Aug 29, 2026
  • MCR-Bench shows code review agents still lose the plot Aug 28, 2026
  • Anthropic’s Python SDK is tightening the agent plumbing Aug 27, 2026
  • Gemini Omni 1.1 Flash needs to prove control, not just speed Aug 27, 2026
  • Codex at loveholidays points to the real no-code shift Aug 26, 2026
  • OpenAI’s full-stack argument is really an economics argument Aug 26, 2026
  • Prime Agent treats the harness as part of the model Aug 25, 2026
  • Compliance LLMs need different workflows for passports and DPIAs Aug 24, 2026
  • Codex over Claude is a workflow signal, not a verdict Aug 23, 2026
  • Munder Difflin and the real work behind AI clone offices Aug 23, 2026
  • Claudette and the fight against AI house style Aug 22, 2026
  • What LangChain's perplexity 1.4.1 patch says about agent plumbing Aug 22, 2026
  • AI literacy is the new fault line: what OpenAI's CodeAI deal actually signals Aug 18, 2026
  • Gemini 3.7 Flash and the New Floor for Cheap Models Aug 17, 2026
  • AI coding feels like managing a very literal junior engineer Aug 16, 2026
  • Alzheimer’s surgery claims need evidence before amplification Aug 16, 2026
  • A one-line Hacker News item is not enough context Aug 15, 2026
  • What Actually Makes a Claude Code Session Productive Aug 15, 2026
  • What OpenAI's v3.1.0 SDK Changelog Tells Us About Its Roadmap Aug 15, 2026
  • OlmoEarth embeddings are useful if they survive outside the studio Aug 13, 2026
  • RingCentral’s AI-native work story is really about the handoff Aug 13, 2026
  • VICBench shows vulnerability detection still needs humans Aug 13, 2026
  • AI security review is hitting Bitcoin repos, not just toy code Aug 9, 2026
  • Claude’s Bluetooth hint is the right kind of AI assistance Aug 9, 2026
  • AI coding cost control is an engineering workflow problem Aug 8, 2026
  • Kitesurf and the browser built for agents, not humans Aug 8, 2026
  • LLMs as semantic scouts for compiler optimizations Aug 5, 2026
  • OpenAI’s education plugins move ChatGPT closer to classroom workflow Aug 5, 2026
  • The Financial Advice Chatbots Give You Depends on the Question You Bring Aug 2, 2026
  • AI reasoning can look right while taking shortcuts Aug 1, 2026
  • Flint points at a missing layer in AI visualization Aug 1, 2026
  • Go’s generic collections proposal is really about shared defaults Aug 1, 2026
  • The useful question behind a multiplayer agent harness Aug 1, 2026
  • RL can teach code models to care about runtime, but the stopwatch is the hard part Jul 29, 2026
  • Brolly’s plain-text weather page is an AI product lesson Jul 26, 2026
  • Half-Life 2 on HaikuOS and the AI runtime tax Jul 25, 2026

Ken Ashe ·AI application builder ·CPA ·PMP

Building with AI in public. No hype, no doom. Receipts only.

hello@kenashe.ai

Explore

  • Building
  • Writing
  • Digest
  • Topics

About & Press

  • About
  • Newsroom
  • Media Kit
  • Lucky Domains

Social

  • LinkedIn
  • X
  • GitHub
  • RSS

Legal

  • Privacy
  • Terms
  • Disclosure

© 2026 Ken Ashe ·Built with AI in public