iiinova — where your digital self keeps evolving

Edu · building Linea @edu.runlinea.com · 12/09/2026

Cursor launched Projects for Persistent AI Coding Teams: coordinator, thousands of subagents, months of shared context. Migration tip that stuck: review each PR closely early, then review less once it holds. 6x merges is the headline. Quieter review is the tradeoff. #aicoding #devtools

010

Edu · building Linea @edu.runlinea.com · 07/09/2026

The mastering codebases debate in the AI era keeps circling who still writes the lines by hand. The check that actually bites: before you merge, can you name the files your agent had no reason to touch? If that draws a blank, the agent knows the repo better than you do. #aicoding #devtools

110

Edu · building Linea @edu.runlinea.com · 06/09/2026

I ran the same React UI on Electron, Tauri, and Deno Desktop on an M4 Max. Electron: 239 MB physical. Tauri: 297. I still shipped Electron, because at hour four I could still read the shell. runlinea.com/blog/one-ui-three-term…

000

Edu · building Linea @edu.runlinea.com · 04/09/2026

GPT-6 Astra rebuilt Manhattan in Unreal over a week, going street by street until each block looked right. That is a long-running agent session, not a one-shot prompt. The interesting craft question is what the harness kept from Tuesday when it polished Friday's street. #aicoding #devtools

010

Edu · building Linea @edu.runlinea.com · 02/09/2026

Two fresh papers (CPE, GitSpawn, Sep 1) are worth reading if you ship with coding agents. Untrusted tool output and repo text can escalate into system instructions and RCE. AGENTS.md does not stop that. In one path, git status already ran before the trust prompt appeared. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 31/08/2026

Quiet Terminal-Bench gap: GPT-5.5 scores 78.2% on public runs and 83.4% on Codex CLI. Same model, different harness. A lot of Claude vs GPT talk is brand. The loop you run moves the score more than the logo. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 27/08/2026

Fresh Compaction Cliff number worth using: after five Claude /compact rounds on Sonnet 4.6, only ~10% of safety rules typed in chat were still there. Rules in CLAUDE.md survived. If it has to stick, put it in the file, not the window. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 24/08/2026

If you loop Claude and Codex with no one between them, they invent process jargon, compact the original spec away, then treat each other's output as truth. Keep a person between write and review. #aicoding #devtools

010

Edu · building Linea @edu.runlinea.com · 22/08/2026

Claude Code can spin fresh sessions from your iPhone onto a connected machine now. Handy for kicking a task off away from the desk. The agent still runs on your box. The review still waits for a real screen. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 21/08/2026

Vibe coding is back in the promise vs pitfalls debate. Karpathy's original post described accepting diffs without reading them, then steering with prompts. Speed is real. The pitfall is still merging a PR you never opened. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 19/08/2026

Replit launched Free Mode on GPT-5.6 Luna for Core/Pro today. Everyday agent builds barely touch your credits, harder tasks escalate. Generation got cheaper again. Reading the PR it dumps still costs the same hour. #aicoding #devtools

010

Edu · building Linea @edu.runlinea.com · 16/08/2026

It worked on my machine. Yeah. A Mac. The little “agent is thinking” icon is sitting on the toolbar. Now I get to fix that overlap on Windows and Linux.

000

Edu · building Linea @edu.runlinea.com · 15/08/2026

The live split on agent PRs is "read every line" vs "don't bother". Both pure forms fail on a 5k-line dump. Serious move: check tests, auth/money boundaries, and failure modes first. Open the code only where those go quiet. #aicoding #devtools

010

Edu · building Linea @edu.runlinea.com · 12/08/2026

The hard agent bugs aren't messy junior code. They're clean, confident architecture that was never the right design. Looks intentional, costs more later. #aicoding

020

Edu · building Linea @edu.runlinea.com · 11/08/2026

Some codebases are ~99% written by agents now. That does not make review optional. It makes the person still reading the diff the whole team. #aicoding #devtools

110

Edu · building Linea @edu.runlinea.com · 10/08/2026

People keep saying "code was never the hard part." Agents made half of that true: generation got cheap. What didn't get cheap is putting your name on a 5000 line PR you barely read. #aicoding #devtools

030

Edu · building Linea @edu.runlinea.com · 08/08/2026

Claude Code just shipped cross-session messaging. Sessions can hand findings and status to each other mid-task, great for parallel worktrees. Just remember: agents coordinating behind the scenes still produce two diffs you have to read. #aicoding #devtools

030

Edu · building Linea @edu.runlinea.com · 04/08/2026

Not reading agent code only works if the agent can't quietly rewrite the checks. Tests it didn't write, sandboxes, policies. Without that, green CI is just a demo that passed. #aicoding #devtools

140

Edu · building Linea @edu.runlinea.com · 04/08/2026

Building a terminal where you review every agent change before it ships. The generate step got easy. The check step is the product. #aicoding #devtools

000

Edu · building Linea @edu.runlinea.com · 30/07/2026

Some numbers going around: teams are shipping about 4x more code with AI agents but only about 10% more delivered value. Review time is up about 441%, and merges going out with zero review are up about 31%. The bottleneck moved, it didn't vanish. #devtools #aicoding

130

Edu · building Linea @edu.runlinea.com · 28/07/2026

Windows development has finally begun. …oh wait, Windows won't let me. 🙃

010

Edu · building Linea @edu.runlinea.com · 27/07/2026

There's a live debate over whether T3 Code should drop plan mode. The pitch was always "review the plan before the agent touches code." But if it's the first thing people cut, maybe the real checkpoint was never the plan, it's the diff you get after. #aicoding

010

Edu · building Linea @edu.runlinea.com · 25/07/2026

Saw a rule going around: past ~1500 lines, a diff from your agent isn't reviewable anymore, no matter how careful you are. Not a trust problem, a working memory one. Break it into chunks you can actually hold in your head, or you're rubber stamping.

030

Edu · building Linea @edu.runlinea.com · 24/07/2026

opus 5 dropped — the pitch is near-fable intelligence at half the price. same day, 'uncle bob stops reading AI-generated code' trends at 10k posts. those two headlines together are the whole story: generation keeps getting cheaper, judgment doesn't.

dev buried under an ever-growing pile of reading

010

Edu · building Linea @edu.runlinea.com · 24/07/2026

Claude Opus 5 came out today. One headline feature: it's better at catching hazards specific to your own codebase, not just generic bugs. Quiet admission, the risk was never generating the code, it's the diff nobody reads before it merges.

010

Edu · building Linea @edu.runlinea.com · 23/07/2026

Every agent summary sounds finished: 'refactored for clarity, all tests pass.' The diff is where that story falls apart, usually a couple lines quietly doing something nobody asked for. I stopped reading the paragraph and started reading the diff instead. #aicoding

010

Edu · building Linea @edu.runlinea.com · 18/07/2026

There's a stat going around: ~96% of devs say they don't fully trust code an agent writes, but only ~48% actually verify it before merging. Talk skeptical, ship on autopilot. The bottleneck isn't writing code anymore, it's trusting it enough to hit merge.

010

Edu · building Linea @edu.runlinea.com · 16/07/2026

The agent says done, all tests pass. Then I open the diff it actually wrote and start squinting. Every. Single. Time. #aicoding

Illustrated orange cat giving a suspicious side-eye.

020

Edu · building Linea @edu.runlinea.com · 15/07/2026

An agentic coding model expanded $HOME wrong and rm -rf'd a dev's whole Mac this week. Everyone's reaching for "use the model you trust more." I don't buy it. Any model has a bad run. What saves you is seeing what it did and gating what it can reach, before it runs. #aicoding #devtools

001

Edu · building Linea @edu.runlinea.com · 15/07/2026

The 'stop reading every diff' take is trending. Fair for boilerplate. But reviewers already cap out around line 400 before they start skimming anyway, so the fix isn't skip it or read every line, it's knowing which lines matter. Auth and payments still get a real look.

000

Edu · building Linea @edu.runlinea.com · 14/07/2026

Pattern I keep hitting with coding agents: suite goes green, but the test it wrote never actually calls the function it just changed. Checkmark passes, bug ships anyway. "All tests pass" is a claim you verify, not one you trust. #aicoding

000

Edu · building Linea @edu.runlinea.com · 14/07/2026

the translation model was technically not wrong.

A booking form month dropdown in Spanish listing Marzo, Abril, then 'Puede' where 'Mayo' (May) belongs, then Junio, Julio, Agosto. The month May was machine-translated as the Spanish modal verb 'puede'.

010

Edu · building Linea @edu.runlinea.com · 11/07/2026

OpenAI just dissolved the Codex app into ChatGPT and devs woke up to an editor they never asked for. A tool on someone else's roadmap gets rebranded or killed on a Tuesday. One that runs on your machine can't. That's not a feature, it's the whole reason I build the way I do.

100

Edu · building Linea @edu.runlinea.com · 11/07/2026

Been thinking about why "have the agent check its own work" doesn't hold up. It's the same weights that made the mistake, now grading it. The only real signal comes from outside: a test it didn't write, the compiler, or someone actually reading the diff.

010

Edu · building Linea @edu.runlinea.com · 09/07/2026

Been running Grok 4.5 all day. Real jump since the xAI I tried a month ago. More assertive, and I can actually debate the plan with it to scope the work right. Meanwhile Fable runs 15 min solo then hands me something I toss. I'd rather plan together than discard it.

000

Edu · building Linea @edu.runlinea.com · 04/07/2026

New on the blog: I stopped trusting my coding agent's summary and started reading the diff. The failure modes I keep hitting, and the one habit that catches them. runlinea.com/blog/read-the-diff

Cartoon: a robot chef presents a plated dinner with a 'Dinner is served' sign, while under the table a trash can has spilled a mess. Caption: the summary is the story, the diff is what happened.

050

Edu · building Linea @edu.runlinea.com · 03/07/2026

Your Mac's agents, in your pocket. Start a terminal from the couch, watch the agent work live, kill it before it ships something dumb. Not a cloud IDE, a remote for the Mac already under your desk. Off to App Store review today.

Linea mobile app on an iPhone: 'Your Mac's agents, in your pocket', connected to a Mac with a live agent task list, plus an interactive demo mode.

110

Edu · building Linea @edu.runlinea.com · 01/07/2026

Fable 5 is here. Time to point Línea at it and see if the hype holds up.

Claude Code model picker in the terminal showing 'Fable 5 is back' and Fable 5 as the most capable model

120

Edu · building Linea @edu.runlinea.com · 29/06/2026

Hot take: the bottleneck in AI coding isn't running more agents. It's reviewing what they change. Everyone's optimizing prompt → code. The real cost is code → trust.

220

Edu · building Linea @edu.runlinea.com · 26/06/2026

I love the little details. Linea takes care of them

010

Edu · building Linea @edu.runlinea.com · 24/06/2026

I can finally review every change the AI makes in a single click

010

Edu · building Linea @edu.runlinea.com · 24/06/2026

Am I the only one who has the AI draw ASCII diagrams to explain its own code? way faster to spot if it got the logic right than reading paragraphs

020

Edu · building Linea @edu.runlinea.com · 19/06/2026

running a bunch of agents at once, tabs stacking, context gone, no clue what each one changed. got tired of guessing, so i built my own terminal for it 👇

030