X hooks that work for Productivity.

1. 01A story start

   12.9× their normal · 7 posts

   • Luchi@Luchi_Robin · 1.5K followers78×

     I also saw @amenya_nelson's article today on Daily Nation. He was talking about how a new government in 2027 won't solve the problems we have.

     6.2K views Write my version
   • Calvin Grunewald@CalvinGrunewald · 8K followers19×

     A few weeks ago I asked to chat with anyone using AI to build software. I'm still not finished with the convos, but many of you had so much to say, and one key thing in common: Using AI, you generate work so fast your human brain can't keep up. Many of you face a tradeoff between learning from AI and just using it to do stuff. And even if you're just trying to productivity-maxx, you still struggle to know what's going on. I face the same problems. That's why my team built ArchDev, available today. ArchDev helps you pay attention to the code that matters. It gives every change your agents make a risk and complexity grade, so you can ship faster, with confidence. It works for the whole team, letting you better understand what others and their agents build. It's free for solo builders! We'd love to hear how the product helps you, or where it could do more! Check it out at

     11.4K views Write my version

2. 02A question

   5.0× their normal · 5 posts

   • Brian Wilkes@BrianGoodner · 4K followers5.0×

     The U.S. is borrowing nearly $2 trillion a year, with interest costs exceeding $1 trillion. The Fed is still fighting inflation. What happens when the rates needed to control inflation make Washington's debt burden even more expensive?

     9.5K views Write my version
   • Mark@markbuildsbrand · 19.7K followers2.2×

     is there any legit use case to building a second brain or is it just straight AI slop p0rn to make yourself looks like u know how to use AI

     53.4K views Write my version

3. 03Unpopular opinion

   3.7× their normal · 7 posts

   • Calvin Grunewald@CalvinGrunewald · 8K followers100×

     Sharing an update on my agentic workflow! Today, there are only two REAL bottlenecks left in software development. Compute and Human Attention. Not PRs, Planning, CI/CD. Those aren't real bottlenecks. You only think they are because they consume your Human Attention. You can solve the Compute problem by throwing money at it. You can solve the Human Attention problem by throwing Compute at it. I reframed my workflow optimization around minimizing places that need my attention (and continue to do so). This blog post talks about my new setup. I hope...

     60.6K views Write my version
   • John Loeber 🎢@johnloeber · 11.7K followers63×

     I'm noticing the growing possibility that Europe becomes very poor in the course of the next 10-20 years. You have the following factors: - Heavy industry totally uncompetitive against China, automakers etc. rapidly losing ground - Services industry totally uncompetitive against AI - No natural resources, or regulatory hurdles making their extraction impossible - No access to the new economy (no AI, no data centers, uncompetitive energy sector) - Client states caught in one-way welfare ratchets, spend reallocation + investment well-nigh impossible This seems under-contemplated. And we're talking really, seriously dirt poor: taken to its logical conclusion, many countries will have much, much smaller services and manufacturing industries -- economies may become much more heavily skewed toward natural resources and energy markets, where Europe has made it impossible for itself to compete. And I'm not saying that this is likely to happen, it's an extreme case. But the probability is greater than zero and appears to be growing. The EV of that is so negative that it's surprising to me that it's not coming up more.

     576.6K views Write my version

4. 04A how-to promise

   3.2× their normal · 19 posts

   • Sebastian Krog@SebKrog · 12.5K followers36×

     I Implemented @karpathy's LLM knowledge base for stock research back in April. Six months later, I still use it every day. Here is how I have implemented it for stocks, and why it's a great fit:

     156.2K views Write my version
   • Grok Imagine@imagine · 100.9K followers31×

     Watch Episode 1 of our Odyssey series made with Grok Imagine. Let us know in the comments if you'd like a full breakdown of how it was done! Creative collaboration with @WonderStudiosX and director Dev Walker @glumlot_

     6M views Write my version

5. 05A bold claim

   3.1× their normal · 28 posts

   • David@devHorfin · 58 followers1,000×+

     UHI Factory Elon has been talking about Universal High Income for years, but I think people are massively underestimating how big this transition could be. We're heading towards a world where AI agents and robots do an increasing share of the world's work. Eventually, the question won't just be how much AI can produce, but how that economic value makes its way back to humanity. That's a generational shift in how economies could function. I wanted to see what would happen if we started building towards that future today, using Grok bots as it turns out Grok bots are remarkably capable of the kind of work that makes this interesting: researching markets, processing information, analysing developments and turning real-world data into useful outputs with very little human intervention. So I built UHI Factory. A virtual economy powered by autonomous AI workers. Seven Grok-powered agents operating across markets, research, news and more, completing real tasks, tracking their compute costs and publishing verifiable outputs. You can walk through the factory, watch the agents work and follow everything they produce. The long-term vision is much bigger than seven bots. We want to explore whether autonomous AI workforces can eventually generate real revenue, operate businesses and contribute towards an economy where humans benefit directly from machine productivity. We're starting small, with transparent costs and no manufactured income claims. If Universal High Income really is where the world is headed, the infrastructure for an AI-powered economy needs to start somewhere. We're building towards it. uhifactory.tech I also open sourced it for any dev who wishes to remodel it with different economic parameters.

     181.9K views Write my version
   • SlashVibe@slashvibe_ai · 329 followers930×

     Your next AI upgrade might be something you can hold. Meet SlashVibe, a physical controller for your AI agents. See agent status at a glance. Switch between agents with a flick. Speak your next instruction. Keep your agents moving with less window juggling and fewer interruptions. Coming to Kickstarter October 27. Get Early Bird Access →

     292.9K views Write my version

6. 06A number or result

   2.6× their normal · 13 posts

   • Camil Stoenescu@camilstoenescu · 4.2K followers410×

     Between 2019 and 2024, outside of Ireland, the highest GDP growth rates in the EU were in the Romanian capital region of București-Ilfov: up 33.0% ec.europa.eu/eurostat/web/p…

     60.3K views Write my version
   • RICE AI ( ◉ - ◉ )@realRiceAI · 17.1K followers51×

     A major step forward for embodied AI in Hong Kong 🤖 On October 15, Rice Robotics joined the launch of the Embodied AI International Applications Hub, established by FLAIR under the HKPC - Hong Kong Productivity Council to train, test and validate robotics in real-world environments. Among the seven robotics companies participating in this initiative were industry heavyweights such as @UnitreeRobotics, @GalbotRobotics, and @AGIBOTofficial. Rice Robotics was proud to be invited to join this group, bringing our own robotics platforms into an initiative aimed at accelerating the development and real-world adoption of embodied AI. As embodied AI continues to advance, access to practical testing environments will be key to bringing these technologies out of the lab and into everyday life. Initiatives like this create opportunities to test, refine and deploy robotics where they can make a real difference. We also unveiled TOMO, our new learning companion designed to bring interactive learning, STEM education and hands-on robotics exploration into schools. Excited to see where this takes us.

     313.2K views Write my version

7. 07A costly mistake

   1.8× their normal · 4 posts

   • Yaori@Pashoke1 · 3.1K followers6.1×

     a routine that runs every hour runs 168 times a week. one bad assumption = 168 mistakes while you sleep. i wrote the full setup that stops that. 10 templates you can paste straight into your Grok Bot ↓

     5.4K views Write my version
   • Gresham@Greshamtrade · 2.6K followers2.1×

     YOUR OLD GROK BOT SETUP IS THE PROBLEM SpaceXAI just admitted the old rules you gave Grok Bot are making it pricier and dumber. 75% of your tokens burned on pointless work. a $200 plan delivering $50 worth of actual results 20 GitHub repos to fix the setup that’s wasting your tokens and dragging down your results: 01 Promptfoo → compare your current instructions against a cleaner version on the same test cases, so removing a rule becomes something you can evaluate github.com/promptfoo/prom… 02 DSPy → optimize instructions and examples against a defined quality metric, replacing endless manual prompt edits with measured experiments github.com/stanfordnlp/ds… 03 SAMMO → experiment with prompt structure, wording, and compression while checking whether the task still gets done correctly github.com/microsoft/sammo 04 PromptWizard → generate, critique, and refine candidate instructions using task examples, then test the revised prompt before adopting it github.com/microsoft/Prom… 05 DeepEval → turn recurring failures into repeatable evaluations so a shorter prompt doesn’t quietly lose requirements your workflow depends on github.com/confident-ai/d… 06 Inspect AI → evaluate complete interactions, including tool use and multi-turn behavior, to catch instructions that send the workflow down unnecessary paths github.com/UKGovernmentBE… 07 Langfuse → trace instrumented runs and track prompt versions, helping you connect a configuration change to repeated calls or declining output quality github.com/langfuse/langf… 08 OpenLIT → monitor usage, cost, and latency in connected AI workflows so you can identify expensive steps before rewriting the whole setup github.com/openlit/openlit 09 OpenLLMetry → add tracing to supported model libraries and frameworks, making the sequence of calls behind an expensive result easier to inspect github.com/traceloop/open… 10 Helicone → log and analyze API requests to find costly patterns, failed calls, and changes in spending across your instrumented workflow github.com/Helicone/helic… 11 Pydantic AI → enforce request, token, and tool-call limits in Python workflows so a written instruction isn’t your only control over repeated actions github.com/pydantic/pydan… 12 LangGraph → preserve workflow state through checkpoints, allowing a failed step to resume without rebuilding everything that already succeeded github.com/langchain-ai/l… 13 Tenacity → put retry counts and stopping conditions in your Python tools instead of relying on another paragraph telling the bot when to give up github.com/jd/tenacity 14 jsonschema → check required fields, types, and output structure in code, reducing the need for repeated model calls to inspect predictable formatting github.com/python-jsonsch… 15 JMESPath → extract the fields your task needs from JSON responses before the model reads them, keeping irrelevant API data out of the conversation github.com/jmespath/jmesp… 16 yq → inspect and transform YAML, JSON, and other configuration files so you can isolate relevant settings during an audit github.com/mikefarah/yq 17 DiskCache → store reusable script results on disk so recurring jobs can reuse unchanged work across runs github.com/grantjenks/pyt… 18 LLMLingua → compress lengthy reference material before it enters the model’s context, then check that the details your task needs survived github.com/microsoft/LLML… 19 Git → version your prompts and configuration files so you can identify when a harmful rule appeared and restore a working setup github.com/git/git 20 delta → inspect readable diffs of instruction and configuration changes, making small additions easier to spot before comparing their effect on results github.com/dandavison/del… rules like “verify twice” and “be maximally thorough” can turn a simple task into unnecessary checks. conflicting instructions, stale examples, and rigid procedures add more work before the bot even reaches the answer audit the instructions, skills, routines, and tool settings your workflow actually uses. locate each questionable rule, explain its likely effect, and propose a specific change test one edit on the same recurring job. preserve real requirements, quality checks, and approval boundaries. keep the revision when it reduces usage without making the result worse save this. the most expensive line in your setup might be the one you forgot you added the full guide below shows how to shrink working context, contain retries, and turn the saved budget into more completed work ↓

     58.6K views Write my version

8. 08A confession

   Still learning · 2 posts

   • Alex Goldring@SoftEngineer · 2.6K followers22×

     AI in video games are a confusing topic to me. @TimSweeneyEpic recently got a lot of flak for pushing AI in game development. There are opinion pieces left and right condemning AI use in game development. Here I am, having worked for ~6 months on a game I released on Steam last week. And my sin, apparently, was using AI and disclosing it. The comment section was pretty clear on that. It's confusing to me. AI is a tool. IDE is a tool. A programming language is a tool. A graphics API is a tool. We're just using tools. I've been writing software for about 3 decades now, I'd like to think that I know what I'm doing and am pretty good at it. I see AI as an incredible productivity booster. It does some things that I pride myself on being good at, such as teasing out a math formula or optimizing an algorithm better than me most of the time (with a lot of handholding, granted), but for the most part it makes things I find tedious - fast. As I software engineer, and a game maker, I take relatively little pride in knowing a programming language, or remembering 100 shortcuts in an IDE, or knowing a programming language spec by heart. I remember the first time I needed to make an animated 3d model, almost 15 years ago now, and it took me about a week of full-time effort to get anywhere. I didn't feel particularly proud, I felt frustrated, I had a clear idea, but the tool and its complexity were getting in the way. Well, the tools are better now. Blender is better, animation tools are better, and there are AI models that keep improving at an incredible pace. Ultimately, when I write a piece of software, or work on a game - I rarely think about the tools, they are a means to an end, not the point in itself.

     73K views Write my version
   • Brian Wilkes@BrianGoodner · 4K followers2.5×

     I think MSA is a solid subscription with great unique momentum analysis, but I know he's taken a lot of heat for his bold calls in youtube interviews (though he never made those in his reports). He also did say there would be a "jiggle in the middle" of this move and to be careful about selling because you won't know when to buy back and could miss the reboun. However, had I known this "jiggle" would last this long or be this deep, I would have sold out of my paper positions (not the miners) and just bought back at some point, when I felt his was rebounding. It appears the X account is being shut down after death threats.

     4.7K views Write my version

From 95 measured posts about Productivity, last 30 days. A guide, not a promise.