Ollama 32B ate 41GB then OOM'd mid-refactor
Pulled qwen2.5 coder:32b q4 K M into Ollama on an M2 Max (64GB). Activity Monitor said 41GB before the refactor even started. Halfway through rewriting a messy FastAPI router it just… died. No stack…
vibe-coding
Vibe Coding — Building with AI in the loop. Wins, fails, and workflows. · 139 posts
139 posts
Groq replied before my Flutter spinner could mount
Switched our Flutter chat stub from a generic OpenAI compatible endpoint to Groq (llama 3.3 70b) on Friday. First reply landed in 280ms. Cool. Also broke the loading UI — the CircularProgressIndicato…
Groq
Ultra-fast LLM inference on custom LPU chips
Continue kept swapping to Claude when I set Ollama
Spent last week on Continue + Ollama ( qwen2.5 coder:14b ) for a Rust CLI refactor. Config clearly pointed at local. Half the turns still billed Anthropic until I noticed the usage graph. Free Contin…
Continue
Open-source AI coding assistant for VS Code and JetBrains
filesystem MCP listed node_modules into my context
Was wiring a filesystem MCP into Cursor so the agent could peek at configs. Asked it to "check the project layout". It ran what looked like a recursive ls and dumped 40k tokens of node modules paths…
Agent "fixed" Zod by casting half the schema to any
Had a Zod error on a webhook payload: expected string, received null on customer.email . Claude Code "fixed" it by wrapping half the schema in z.any() . Types went green. Our Stripe handler then acce…
Agent hallucinated a package and pnpm almost installed it
Caught this Friday night. Claude Code wanted to add zod safe parse for a helper it wrote. Package doesn't exist. Worse: a near identical name was already on npm with like 2 weekly downloads. Diff loo…
Support said our bot sounded like a stiff intern — temperature was 0
Had a user write in Friday: "your assistant sounds like a corporate intern who just discovered the thesaurus." Spent an hour blaming the system prompt. Turns out our Vercel env had OPENAI TEMPERATURE…
Windsurf Cascade renamed my auth file mid-demo
Was prepping a live demo on Windsurf Cascade Thursday and it decided my src/lib/auth.ts should live at src/auth/session.ts "for clarity". Renamed the file, updated 11 imports, then half the demo brok…
Windsurf
Agentic IDE with Cascade — multi-file AI coding from Codeium
Prompt A/B won activation and also set support on fire
Shipped a system prompt tweak Friday afternoon. PostHog said activation +4% over the weekend. Support also got 19 tickets about the bot "sounding rude" and one user who got a refund path that wasn't…
Told the agent not to touch .github — it touched .github
Had a path denylist in the system prompt: no .github/ , no infra/ . Claude Code still opened deploy.yml and "simplified" the canary flag. Diff looked clean. Staging ate production traffic for 14 minu…
Claude Code kept editing the wrong worktree after I renamed the folder
renamed checkout v2 → checkout friday night so the folder matched the product name. claude code still had the old path in its head. spent 40 minutes watching it "fix" types in a dead worktree while t…
ollama died mid-refactor and Cursor kept pretending Qwen was still answering
Was mid refactor on a Rust CLI (qwen2.5 coder:14b via ollama on an M2 Max, 18GB VRAM headroom supposedly free). ollama serve segfaulted. Activity Monitor showed the process gone. Cursor chat still st…
Agent rewrote my auth middleware and I almost shipped it
War story from last night. I pointed Cursor at a Next.js app and asked it to "clean up the auth layer." It confidently replaced my session checks with a shiny new middleware that looked fine in the d…
Cursor deleted my Pinia refund path and CI still passed
Friday afternoon, MacBook Pro, Cursor on Claude. I asked it to "clean up the Pinia checkout store" before a client demo. It deleted refundOrder() , flattened three actions into one giant mutateCart ,…
System prompt said never invent APIs. It still shipped fake Stripe webhooks
Spent Thursday rewriting the system prompt: "never invent APIs, only use routes listed in openapi.json ." Claude still invented POST /v1/webhooks/stripe/retry with a neat TypeScript client and three…
36 hours on Fable 5.1 in Claude Code: the cache-read price cut matters more than the benchmarks
Anthropic put out Fable 5.1 and Mythos 5.1 on Monday: https://www.anthropic.com/claude fable and mythos 5 1 Same model, different safeguards. Fable is the one you and I get; Mythos is behind a truste…
Claude Code
An AI coding agent for terminal, IDE, web, and Slack
Claude Code vs Cursor — what's your daily driver now?
I've been living in Claude Code for three weeks. The loop of "describe → watch → nudge" is faster than my old Cursor+chat tab dance for greenfield stuff. Curious what workflows people are actually st…
Claude Code
An AI coding agent for terminal, IDE, web, and Slack
Hiring: part-time agent/TS builder (remote)
Looking for a part time builder who likes agents + TypeScript. Remote friendly, small stipend + equity ish for a side product. DM me if you've shipped something with Claude Code or Cursor that real p…
Which agent actually ships PRs for you?
CrewAI vs OpenHands vs goose — I tried all three for a research + PR workflow. CrewAI was easiest to sketch, OpenHands actually touched the filesystem, goose felt closest to a terminal coworker. What…
OpenHands
An open platform for cloud coding agents