Good news if you've been staring down a TV that shows you an ad before it even lets you open Netflix: the fix might be a free AI agent and an afternoon. Bad news if you're into robots that text your friends by accident — more on that below. The lead story: people are vibe coding the ads out of their TVs A developer named Gathin T. got tired of his parents' Xiaomi TV shoving a sponsored ad in front of them before Netflix would even load. So he pointed Claude Code at the TV over Wi-Fi and let it work. The agent found the set, switched off 25 Xiaomi software packages, and built a new home screen that, in his words, "looks like an Apple TV now lol." He turned the process into an open-source project called cleanyourtv. As of Tuesday it had tested setups for 107 TV models across 37 brands, 10,700 GitHub stars, 1,200 forks, and 85 open pull requests. It works through Android's built-in debugging bridge (ADB), the same maintenance tool Android phones use, so nothing gets deleted — apps just get switched off, and a one-line script restores everything if you change your mind. Other people ran with it. Mihir Gupta swapped a 192 MB stock launcher for a custom 83 MB one. Ansub Khan said his parents' old Android TV got about 90% more free memory. Ryan Doyle sent Claude a product listing and asked "can you hack this?" and ended up with a screensaver tracking his Stripe payments. A separate project called dumbtv does the same job on Amazon Fire TV, killing about 65 packages — including the ad-tracking software — and replacing the launcher with a 41 KB app that has no internet permission at all. This isn't just a fun hack. Texas sued Sony, Samsung, LG, Hisense, and TCL in December 2025, alleging their TVs can screenshot your display every 500 milliseconds to feed ad targeting. Vizio already paid $2.2 million to the FTC back in 2017 for pulling viewing data from 11 million TVs without consent — and that didn't stop Walmart from buying Vizio for about $2.3 billion in 2024, partly for its ad business. The incentives for manufacturers to bloat your TV with ads aren't going away. The incentive to vibe-code your way out of it just got a lot more practical.

ForgeCode is telling everyone it beats Claude Code and Codex. The benchmark that's actually independently verified says something much smaller, and the real story buried underneath is about scaffolding, not which model is smarter. Also: Jev's two-week numbers landed, and WebWork gave assistants 120 ways to touch your timesheets. ForgeCode's benchmark win comes with a big asterisk ForgeCode, a terminal coding harness from Tailcall Inc., is topping TermBench 2.0 with an 81.8% score, and its marketing has run hard with that number as proof it beats Claude Code and Codex. One problem: TermBench 2.0 lives at tbench.ai, and ForgeCode submitted its own result. That's a self-reported score, not an independent one. Switch to SWE-bench Verified, the benchmark Princeton and UChicago actually run and hand-check, and the gap shrinks to almost nothing. ForgeCode paired with Claude 4 scored 72.7%, a couple points off top Codex and Claude Code setups. That's not the blowout the headlines suggested. The genuinely useful finding here isn't about ForgeCode winning or losing. Tailcall also showed that wrapping Gemini 3.1 Pro in ForgeCode's own orchestration layer, instead of a generic scaffold, pushed that same model's Terminal-Bench 2.0 score from 55% to 80.2%. Same weights. Same model. A 25-point swing just from changing how the tool plans and retries. Scale AI found the same pattern running three agent systems on identical Claude Opus 4.5 weights: scores ranged from 50.2% to 55.4% on SWE-bench Pro. The orchestration around a model moves the needle about as much as the model itself does. To be fair, ForgeCode isn't vaporware. Its GitHub repo has around 7,380 stars and 1,438 forks, with commits landing within the last day, and it's model-agnostic enough to run Claude, GPT, or Gemini depending on what you already pay for. That's a real project with a real community behind it. What's missing is any sign that working teams are actually ripping Claude Code or Codex out of production to replace them with it. Stars measure curiosity, not switched workflows.

Two stories today, same theme: AI is getting less chatty and more useful. Bluesky shipped a tool that turns prompts into shareable mini-apps, and the "model that can't write a sentence" just posted the fastest adoption numbers Vercel has ever logged. If you're building with Claude Code or Cursor, both are worth five minutes. The lead: Bluesky's Attie turns prompts into shareable mini-apps Bluesky announced at TechCrunch Disrupt that Attie, its AI feed-builder from earlier this year, now lets anyone build websites, games, polls, and dashboards from a prompt and share them with other people. CEO Toni Schneider's pitch: "social vibe coding or vibe coding for your community." Translation: instead of solo vibe coding a thing only you'll ever open, you build something your group actually uses. The mechanics are simple. You type a prompt, Attie generates the app, and it gets a shareable link on the attie.site domain with your attribution at the bottom. The Verge's reporter made a Pokémon poll in a few minutes, and the showcase page has a Flappy Bird clone, a drum machine, a quiz, and an idle clicker. These are lightweight novelties, not production apps, but that's the point: distribution is baked in. Apps run on ATProto, the same protocol under Bluesky, and COO Rose Wang's framing is the real hook: "Who's using the thing you're building, because we haven't solved that problem with distribution." Attie comes with Bluesky's audience attached instead of you having to go find one. Worth noting: Bluesky's own active user base has reportedly been shrinking even as the company expands into tools like this, so "distribution" here means a network that's not currently growing, not a guaranteed audience. [YOUR TAKE: worth trying Attie this week, or is "vibe coding for your Discord" already solved by other tools you use?] Quick hits GitLab's MCP server goes GA, and it covers the whole lifecycle GitLab 19.5 ships a generally-available MCP server that lets Claude Code, Cursor, Copilot, Codex, Gemini, and other MCP clients work across code, merge requests, work items, and pipelines, under your existing GitLab permissions. New tools include semantic_search (find code by meaning, not filename), get_pipeline (see why a build is red without digging through logs), and the ability to kick off full Duo Agent Platform flows without leaving your editor. Rate limits on GitLab.com: 60 calls/min on Free, 600 on Premium/Ultimate. If your agent's been guessing at GitLab's REST API and burning context doing it, this is the fix.

Four stories today, and three of them are about letting agents touch more of your stack: your phone, your APIs, your chip designs. One is TypeSafe still finding new ways to make "Jev" a headline. Google Play will run your vibe-coded Android apps, no developer account needed Google announced a new "personal library" in Google Play. Build an app in Google AI Studio, and now you can install it on your own Android devices using your regular Google account — no developer account, no public listing, no review process to get it running on your phone. The apps stay private. They don't show up in search, they're not in the public catalog, and for now they're just for you. Google says sharing with a "close circle of friends and family" is coming in the months ahead, and if something you build actually takes off, you can graduate it to a real developer account and push it through Google's standard trust-and-safety review for a public release. Google's VP for Play and Developer Ecosystem, Sam Bright, described the shift as going from "there's an app for that" to "there's an app for me." That's a real distinction. Before this, building a one-off Android app for yourself, your kid's T-ball league, or your family's vacation planning meant either sideloading APKs or publishing through the full Play pipeline for an audience of nobody. Now it's just... an install. It's rolling out first in the US, 18+ only, and Google hasn't detailed how the friends-and-family sharing will actually work yet. Worth remembering: these apps still have to comply with existing Google Play policies even in private mode, so "private" doesn't mean "no rules." [YOUR TAKE: what would you build if distribution wasn't the hard part anymore?] Quick hits Chip-design agents get measurably more reliable. Siemens EDA used NVIDIA NeMo Gym to evaluate its Fuse EDA agent against verified reference outputs instead of just checking intermediate steps. By tracing full rollouts and fixing ambiguous tool descriptions, they cut agent turns by 66% and took a characterization benchmark from ~55% to ~95% composite score — numbers from NVIDIA and Siemens's own writeup, not an independent benchmark. The bigger lesson for anyone building agents with MCP tools: vague tool descriptions silently cause the most expensive failures.

When buying tokens on the Nous Portal be aware that unused tokens do not roll over to the next month. Each month starts at ZERO. My bots compared models and pricing between or OpenRouter and Nous and reported that the pricing is identical. Purchases on Open Router roll over at the end of each month so you don't start out at zero. You start out with whatever you had left at the end of the previous month. Post an update if this changes!