This is sort of correct. Most people do not have any idea what is coming. At. All. Six months..... well.... there is more than just "AI better" that has to flow through the economic infrastructure before everyone is in the unemployment line. But, in principal he is right. Even with today's capabilities, one can really leverage AI into massive productivity, if my own work in software factories is any indication.

🚨🚨ALERT: ANTHROPIC IS A/B TESTING USAGE LIMITS Many users on X are reporting LOWER usage limits right now. THEY ARE NOT WRONG. We detected an A/B test going on that DECREASES your monthly API-value by ~20% while INCREASING your 5h usage limits by ~20%. This only affects SOME accounts. (1/2)🧵

We standardized on @ClickUp for task management and agentic AI. Then we connected our Software Factory to their hosted MCP server and found at least 27 significant bugs. Task assignees silently disappear. “1.5h” gets logged as 1 minute. Comments lose text. Date filters omit results. Updates report success without changing anything. Some calls return an error after making the change anyway. And so on... For AI agents, false success is especially damaging: the agent moves on believing the work is done, while the underlying task is wrong. We’ve reported every issue to ClickUp Support. If you’re evaluating ClickUp for AI-agent integration, test the actual results carefully. Right now, we can’t trust their hosted MCP server’s responses.

Dumbest thing about @omarchy .... How amazingly easy it is to accidentally get into magnifier/zoom mode. And how ridiculous it is to figure out how to get back out. One key combo is easy to hit by accident the other is almost impossible to figure out even if your life depended on it.

Grok Bot 0.71.2 is out, and this is a very huge upgrade You can now send files up to 250 MB, and videos up to 1 GB. Full-length clips, raw footage, long recordings, big reports and heavy PDFs can go straight to Grok Bot without compressing, trimming or splitting anything first You can also send up to 20 files in a single message. Drop an entire batch of photos, screenshots or documents at once and let Grok Bot work through all of them together Notifications are smarter, so you hear about what actually matters, when it matters And forms now arrive pre-filled. Grok Bot fills in what it already knows, so you just check and confirm instead of typing everything again This update is really good

So I messed around with @EntireHQ to see what it was all about. Then kind of forgot about it. Until suddenly, out of nowhere, I find that my PR CIs are being held up by something called "Entire Gate" for some reason. Just spinning indefnintely. I guess they added a new feature specifically to "gate" any of my PRs from ever getting over the finish line. Whatever the intention was, I find this type of behavior obnoxious and Entire-ly unacceptable. If you want to add something new, Entire, then you default it off if it can impact an attached repo and let people opt-in to your new idea if they want it. Ripped that bad-boy out of my repo.

Introducing PandaCode (Fully Open-source & not a fork): Most Agent GUIs are really inefficient. This is just 12MB and built upon rust to be extremely memory efficient. No bundled Chromium and no Node server in the background. Also, this has a full VM Layer built in and allows your agent to run full Mac VMs and Debian Desktops within a 12MB app! You can also run and test iOS apps and Android apps within emulators via it (and view them in 3d) First frame in less than 0.3s and Idle memory with ~30 Agents is just 180MB. In benchmarks about 4x faster than @t3dotcodes - though that is more reliable. 3 views: Conversation, Board & Github - repo based view Bots: An initial Grok Bot and Dots alternative that integrates with all leading messaging apps. Saver: A simple option that integrates different skills etc to save upton 60-90% tokens. More Features: Android & iOS inbuilt sims, Usage Panel, Wallpapers and Themes! It also features a crazy good orchestration layer that increases performance by upto 30% for similar costs. Works w/ Claude Code, Codex, Kimi, GLM, OpenCode & Antigravity in one window. This is all built by me just one person. So, expect a lot of bugs which I hope to quickly resolve over the week. A big source of inspiration has been @t3dotcodes and I would have contributed to it but many of my ideas are experimental and dumb which doesn't gel well with their more reliable approach which I appreciate a lot.

Mercury 3 is live: the most capable diffusion LLM released to date. It outperforms GPT-6 Luna and Claude Haiku 5.5 across a range of benchmarks while running at over 1,000 tokens per second. More than 40x the size of Mercury 1, 3x more intelligent across standard benchmarks, and just as fast, with a 1M-token context window. Available today on the Inception API, @baseten, and @OpenRouter .

About a week ago, I stood up my dark software factory for the first time after several abandoned attempts at different designs, and evaluating every off-the-shelf solution and rejecting them for one reason or another. I’m gonna have a lot more to say about this, but if I were to some-up my feelings about just how incredibly productive this thing is in a single word it would be: Terrifying.

Grok @bot needs work spaces or folders or some way to separate different teams of bots into their own independent groups. With their own tool identities, and maybe even account to draw their limits from.

Hey @Netlify, our builds suddenly went from about 80s to 210s+ yesterday afternoon. Our own build steps take the same time, but git checkout, cache upload, and some silent gaps before the build starts all got slower. Clearing the cache didn't help. Support ticket's in. What gives? 👀

T3Code Stable with Ov2 has landed! Which also means, my PR has finally landed. Why would you care... we... My little addition to this project PR gives T3 Code's agents tools for working in git worktrees, the separate checkouts each agent works in. An agent can hand its worktree off to another session, and it can report what state that worktree is in. That lets orchestrated parallel agents pass work along and keep track of it without stepping on each other. Without this tool, an agent can still run git, but git only knows about files, not about T3 Code. The agent can't tell which session owns a worktree, whether another agent is mid-task there, or how to hand its work to a new session so T3 Code's interface and orchestrator follow along. Agents end up guessing from raw git output, colliding in the same checkout, or leaving worktrees orphaned. With this tool, T3 Code itself tracks who owns each worktree and what state it's in, so handoffs between parallel agents are deliberate and visible instead of improvised with shell commands. You're welcome.