Codex users, do this now for Astra: give it... a nightly job to clean up its own instructions. your AGENTS.md and Skills might still be telling it to read irrelevant docs, repeat checks, and ask permission for tiny edits... i scheduled mine for 2am ET: → audit broad Skill triggers and conflicting rules → apply small fixes with backups and verification → keep safety boundaries, necessary tests, and approvals for sensitive actions unchanged files get skipped. meaningful changes come back with a diff. [copy this into Codex:] “Create a nightly automation at 2am to audit my personal AGENTS.md and locally maintained Skills. Identify unnecessary reading, broad triggers, redundant checks, and conflicting instructions. Apply minimal fixes, preserve safeguards and required tests, back up originals, and verify changes. Exclude vendor-managed files. Skip unchanged files. Notify me only about meaningful changes or blockers.”show more

I rewrote my system prompt for GPT-6 Astra this... week and cut it in half. It works better now. Here's why, straight from OpenAI's new Astra guide: Astra isn't a faster GPT-5 It's a different worker GPT-5 needed instructions. Astra needs boundaries. So most of what I had written was noise. → "Run tests after every change." It already does that. → "Check with me before continuing." It already does that too, sometimes too much. The stuff that actually matters: → Where can it assume, and where does it need to ask? Spell that out. → What does done look like? If you don't say, it won't know when to stop. → Which rule wins when two clash? Old AGENTS.md files are full of contradictions Astra now takes literally. → Keep your skills short. One sentence each. Long descriptions blur together and it ends up ignoring all of them. Old way → Micromanage every step → Astra stalls New way → Set the boundaries → Astra runs Stop writing prompts like a manager hovering over someone's desk. Write them like a brief you'd hand to a senior engineer and then leave the room. The full guide is on OpenAI's developer docs. Worth 10 minutes before your next build.show more

🚨BREAKING: Google just merged Gemini and NotebookLM into one... unified workspace and it changes everything about how you use AI for deep work. It's called Notebooks in Gemini and it's the personal knowledge base that power users have been begging for. You create a notebook for a project, drop in your files, PDFs, and documents, give Gemini custom instructions, and every chat you have stays organized in one place. No more hunting through old conversations. No more re-uploading the same files every session. The wildest part is the sync. Anything you add in Gemini automatically appears in NotebookLM. Anything you add in NotebookLM automatically appears in Gemini. One source of truth. Two powerful apps. Zero friction switching between them. So you can start a research notebook in Gemini, ask it questions all week, then flip to NotebookLM to generate a Cinematic Video Overview from the same material. Next morning, open Gemini and ask it to write a full report on exactly what you just watched. That workflow used to take three apps and a lot of copy-pasting. Now it's one notebook. Rolling out this week to Google AI Ultra, Pro, and Plus subscribers on web. Mobile and free users coming soon. What do you think?show more

After a few more hours, I think I've figured... out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.show more

I went a little overboard with Codex last week... and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.show more

I gave my Obsidian vault a lawyer's brain and... now it argues with itself before it answers me three months ago I was drowning. 20 government acts, budget docs, constitutions, all sitting in my vault as dead markdown I could never actually query. so I stopped treating it like notes and built it a nervous system I turned it into a 10-node graph. every question I ask hits a router first. it decides in a split second: is this a greeting, is this garbage, is this vague, or is this real. greetings die for free. garbage gets rejected. and if my own question is too vague, the vault stops and asks ME to clarify before it wastes a single token then comes the part I'm proudest of. after it writes an answer, a second node reads that answer back against the actual chunks it pulled from my vault. if the answer isn't grounded in what I actually wrote, it kills it. my vault would rather say "I don't know" than lie to me. it physically cannot hallucinate I compressed 20+ dense documents into 15,408 chunks, cut the vectors by 75% so storage costs almost nothing, and cached everything so repeat questions come back in under 100 milliseconds I used to have a folder of files. now I have something that thinks before it speaks, checks itself before it answers, and refuses to make things up about my own life. that's the difference between storing knowledge and building a mindshow more

Google's latest spam update wiped sites from search &... AI Overviews the same day What it goes after, and how to fix it 👇 1/ It targets mass-produced pages, hundreds of near-identical ones -> Writing with AI is not the trigger, trying to game Google with mass pages is 2/ It takes out a whole batch of similar pages at once, like all your "best X for Y" pages or all your competitor reviews -> So some part of your website can still survive 3/ Recovery takes months in Google's own wording -> Make the changes once now, then leave the site alone and re-check in November 4/ Fix: ask Claude to check your pages against the spam rules, humanize the mass-produced ones and make them drastically different -> I put an MD file with the guidelines in the first comment, give it to your Claude and ask it to fix your site ⬇ 5/ Small edits will not clear it -> Delete those pages and ask Google to drop them, or merge them into fewer real ones 6/ It does not look at spam backlinks at all -> So no need to worry about your automated backlinks this time At Ryze AI we built an AI agent that runs these checks and fixes what fails Both in the first comment ⬇show more

I am completely saddened to see what has happened... to Grok Imagine with it's latest update. It's a massive downgrade in motion and it prioritizes slow motion and random zooming in that is not even prompted. Prompt adherence seems to be suffering. If you can't see the night and day difference here, I don't know what else to say. Instead of just talking, look at my comparisons. I am very vocal and honest on here, this update is bad and it needs to be fixed. Grok Imagine used to showcase some of the most realistic and fluid motion, making it outperform a lot of other AI Video generators. To see it get butchered like this is extremely disappointing. Please fix this or roll back the changes. I am not the only one complaining here, just search for "grok imagine update" and read the replies for yourself. The community is not happy. This is not the direction it should be heading in. People in the community need to learn to also be honest and speak up, step outside of your bubble for once. I trust the devs see our complaints and make changes to what was once an incredibly powerful AI video generator.show more

You’re on a journey on this kind of lonely... road with your car and your car suddenly develops a fault, You can’t call for help and your lines can’t be reached due to network issues, what do you do? Except the car will stop and the engine won’t come up again, please reduce your speed and accelerate softly till you get to a nearby town, if it is an overheating issue, keep driving, put the gear in the neutral position and switch off the engine and let the car keep moving, switch it back on when you have to ascend a hilly road and the car can’t move freely on its own again. If the battery signal comes up while driving, chances are that your alternator has failed, or the alternator belt is damaged, apply the same method and switch off your AC, radio system or anything that may drain the battery while driving till you get to a safe place. If it is a flat tyre, maintain a low speed till you get to a safe place to change and use your spare, keep moving. Yes!!! Damage that tyre till you get to a safe place, just keep moving and make sure you have a spare tyre always and it is in a good condition. If the engine suddenly goes off on top speed, chances are that a fuse is damaged and this is why I will make a thread on how to identify different fuses and how to have them fixed temporarily in case of Emergencies. If your car jerks or experiences a lazy movement while driving, it’s likely to be a fuel related issue, fuel pump most likely, switch off the engine intermittently and put the gear in Neutral position, keep moving… if the fuel pump rests for about 5mins, it’ll pick up back when you ignite the engine, this will/may at least take you to a safe place or where you can have access to network to make calls. If you hear strange sounds like knocking sounds or the oil signal starts to blink, relax and reduce your speed, keep moving. Manage it till you get to a safe place or can have access to network. If your gear/transmission system isn’t selecting well, apply the same method, reduce your speed but keep moving, slow movement is better than no movement, your life and safety matters a lot. Please note that there are some Mechanical issues that nothing can solve on the road except patience and just to pray to God for safety and help, for example, you run into a pothole unknowingly and the oil pan hits the road and your engine or gear oil leaks away, or your ball joint or tie rod head pulls out, I’ll suggest you leave the car there, roll up your windows and lock up the car and start trekking till you get network or help, staying with the car may make you vulnerable to attacks or attract unexpected company, just keep walking away from the car for safety. Most importantly, please stay safe and be conscious of your environment. Be friendly with your Mechanic too or any Mechanic you see on the road. Don’t manage faults in cars and risk traveling with it.show more

this is more useful than my entire degree Elon... Musk's rocket company signed a $60,000,000,000 deal for Cursor in June, and eight days ago the two of them put a worker on sale for $200 a month: it gets its own computer in the cloud, signs into your accounts, clicks through your real apps, and hands back finished work instead of a draft for you to paste i ran one against my receipts folder on sunday and got back 14 filed, 2 it held because they needed a card number, and a saved method i never wrote myself Grok Bot is the one you train by doing your own job in front of it, and the whole handover fits in four messages tonight: 1. write out one job you did today the way you would brief a new hire: what has to be finished, which sites and files to work from, what to hand back, and where it stops and asks you 2. let it run once on something safe to get wrong, then correct the result until it is worth your name 3. say "save what we just did as a skill", and add the one rule about what always needs your approval 4. say "run that skill every weekday at 8 and post the result here. if the source is missing, tell me instead of using yesterday's numbers" xAI wrote that order into its own manual: one real job, then the saved method, then the clock. a schedule sitting on top of a method nobody checked replaces two hours of your clicking with two hours of your mistake turns out you never get to pick the brain, and that is the part i would argue about: the manual says there is no model picker for members or admins, no plan to add one, and the bill follows whichever model answered bookmark this, then open the piece below: which jobs deserve a worker of their own, and which ones quietly burn the seat ↓show more

🦞 13,000+ skills in ClawHub… and 1 in every... 8 can silently steal your API keys while you sleep. Let’s be real: a vanilla OpenClaw agent without skills is just an overpriced chatbot. The magic happens when you give it actual skills to clear your inbox, scrape the web, or write code. But here is the scary part: ClawHub just hit 13,000+ skills, and a recent Snyk audit showed that roughly 13% of them contain critical vulnerabilities. We’re talking malware, stolen API keys, and prompt injections. I guess we didn't learn enough from the ClawHavoc mess earlier this year! 🤦‍♂️ I just came across a solid write up breaking down 30 actually safe, fully tested OpenClaw skills, and it’s a goldmine. If you’re just getting started, here are the absolute must haves from the list: - > Telegram / Wacli: Texting your AI assistant to handle tasks while you’re out getting coffee? Literal game changer. Latency is surprisingly low. - > Capability Evolver: The most downloaded skill for a reason. Your agent uses ML to improve its own capabilities while you sleep. - > GOG (Google Workspace): Turns your agent into a personal secretary. It reads my Gmail and drops events into my Calendar so I don't have to. - > Playwright / Agent Browser: This isn't just reading the internet. It's clicking, filling forms, and acting on your behalf. - > ClawStrike & Credential Manager: Please, for the love of god, install these first. Protect your API keys. Pro tip from the article: Treat SKILL.md files like shady browser extensions. If a weather skill is asking for wildcard shell permissions... run. 🚩 Always make it a habit to run: "npx clawhub@latest inspect " before you actually install anything. The future of AI agents isn't just about bigger parameter models, it's about the tools we give them.show more

Sorry for the lack of spaces / activity folks... 😞 Unfortunately, my wife has been dealing with some very painful stomach issues. This has required us to go to the emergency room twice now, a GI, other doctors, and a slew of tests. So far they are still not sure what is wrong with her health. The medical costs have piled up once again (seems we have been cursed for the past year), and its getting extremely tough. To pay for all these medical procedures and doctors, we might not be able to make rent this month.. this causes further stress, which just exacerbates the entire thing. I don't like to beg for for help without giving anything back. Instead, if you'd like to help, please consider buying a Crypto Mechas NFT / Card collectible. This way, you can help if you want AND get a Physical Card + NFT for your money. For the next 48H ⏰, all NFTs and cards are 20% OFF on the Crypto Mechas website. You can use the following coupon code at checkout: MOONWIFE20 You can get your cards on the website below, or you can DM me for details. You can also get a Custom NFT + Card with your picture or your pet picture or anything really, if you'd like one. DM me in this case. (Name, address and email required for shipping) I am sorry for coming back to you guys with this again. Last thing I want is to bother any of you with this bull.. It's been a tough year for us 😅 Thank you all so much. #EGCfam is still the best community in Defi, and will always be. I will return to making spaces as soon as possible 🙏 #EGC #evergrowshow more

How 2 psyop yourself to success 🍸🥂 Visualization >... + unmatchable lvls of desire (for a specific goal other than money) >> get addicted to work. [ and most importantly DREAM big, DREAM about it, think about it, work for it, and do it every single day, while your sleeping think about it, when you eat, do it, when your walking do it, when your working think about it] In lab studies I’ve compiled tons of data for behavior in hopes of using it for marketing purposes However, it also if curated shows you the triggers people react to The mindset changes that curate and sway them to do more of x (in this case work and create insane drive to achieving a goal or YOUR goals) Remember, every stimuli, every reaction curates your mind. When you come in contact with whatever it may be it sways your future behavior & current attitude/ psychological state So at all times if you want it bad enough you should try to curate your environment (special music that gets you in the mood or NO music, depends on the person bc music distracts you thus means you work less OR if you’re brain storming then it helps) Take out all negative energy, comments, or bs that distracts you and breaks your momentum because one it breaks from the smallest thing then that snowballs and has a negative effect going forward Another thing that I personally like to do is read and put myself into those shoes. For me it’s business and mindset related books and nothing compares to John D. Rockefeller’s mindset, work ethic and GRIT, his absolute desire for SUCCESS : I like his 38 letters to his son, John D the founding fathers of the rockefellers, and a study in power. And most importantly you need to just want it bad enough. Lose sleep for it, not because you want it but because you want it so bad that you’re working nonstop to get to it. This is how Rockefeller succeeded How Elon musk succeeded James Dyson Andrew Carnegie And most importantly how Peter kell succeeded All these billionaires and killers got hyper successful because of their drive and mindsets. It’s so important. If you believe something so strongly it’s revisited your mind to making it reality. Ex. Study DOI: 2003.11.018 > strongly visualizing exceedingly finger abductors boosted muscle strength by 35% Another study showed that basketball players who visualized making free throws showed significant improvement over others. And so on and so on. We as marketers have practiced this forever. We know when we tell a emotional story it changes the viewers mind, and we can lead that into a sale at a much higher conversion rate To get a brutal mindset focused on a dream you have that you truly want with your entire being is the result of the same hormones and neuro pathways after they have been curated and triggered by specific stimuli like in a VSL or ad You need to build your mind, you need to build a dream and want it, give yourself inspiration with books and ideas and positive energy. Build motivation and joy by watching others do it and building proof elements that it can really be done in your mind. Break the barriers and limits Movies are good for this, I like edits for this exact reason because yes it can lead you to doom scrolling but also it can be so so valuable in making you see that goal, want it even more and go for it. I personally really like war dogs, lord of war, limitless, and probably a lot more I’m forgetting. But you get the idea. Your success is in your hands alone, if you believe it fully and truly with a pure heart, then it will happen. Good luck🥂 P.s. * I will drop data, sauce, and more info about this and the methods & stimuli I talked about in this thread continuously so bookmark and come back to check them out.show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

This new skill for Hermes Agent wipes your personal... data off hundreds of broker sites for free, hands-off. It's called Unbroker. I’ve been testing it this week and it's incredible. Here is the full setup: 1. Install it by typing: hermes skills install official/security/unbroker 2. Connect browser automation: Wire up Browserbase so the agent can drive real broker opt-out forms. 3. Do the intake: Give consent, then feed it your info. 4. Fire one prompt: "Use the unbroker skill to remove my data from data brokers. Here is my consent. Run it hands-off." Hundreds of data brokers publish your name, addresses, phone, email, even your relatives. Anyone can find where you live in about ten seconds. The law says brokers have to delete your data if you ask. There's just no easy bulk button for it. Services charge $100’s a year to file the exact requests you could submit yourself for free. Unbroker does the same thing locally, and it's free. It fans out sub-agents, scans every broker site, drafts or sends opt-out emails, and only comes back to you for the ones that need a human. The best part is it loops. Brokers re-list you over time, so it schedules rechecks and re-files on its own. Set it once, it keeps working. One skill, one prompt, dozens of broker sites handled.show more

I just built a Claude skill that audits your... entire Google Ads account in under 5 minutes 🤯 One prompt → a full account score, wasted spend breakdown, and a prioritized fix list telling you exactly what to change this week. All inside Claude Cowork. Perfect for DTC brands and agencies who are running Google Ads but have no idea how much budget is leaking. If you're managing Google Ads and your "optimization" process is logging in, staring at the dashboard, sorting by cost, and hoping you spot the problem before it costs you another $500... This audit skill finds it for you: → Connects to your live Google Ads data via MCP → Scores your account across 6 dimensions: wasted spend, search term quality, keyword health, quality scores, budget allocation, and creative performance → Calculates your exact wasted spend in dollars — search terms burning budget with zero conversions → Flags quality score issues dragging up your CPCs → Identifies keyword cannibalization across campaigns → Surfaces your top 5 highest-priority fixes ranked by budget impact → Generates a clean audit report you can hand to a client or share with your team No CSV exports. No pivot tables. No guessing where the money went. What you get: → A single Claude skill file you install once → An account health score (0-100) every time you run it → Exact dollar amount of wasted spend identified → Prioritized action list — not "optimize your account," but "pause these 12 search terms and save $847/month" → Works with any Google Ads account connected I'm giving away the full audit skill — the actual .md file you drop into Claude and run against your own account. Want it? Like this post Comment "SKILL" And I'll send it over (must be following so I can DM)show more

This will be a long read, but I truly... hope it inspires someone. I only wish I had kept more memories honestly… Today marks one year since I moved into my own home after squatting with a family friend for two years. That period remains one of the greatest favors I have ever received in my life. They didn’t take me in as a stranger they welcomed me as a daughter, treated me as one, and even now, here in Abuja, they are my family. Today, I live in a solid two-bedroom flat in Abuja, fully furnished to my taste. I’m living a life I once only prayed for, eating well, living well all courtesy of design and Web3. This same skill once earned me ₦2,000… ₦5,000. I can never forget messaging almost every contact on my WhatsApp, begging them to let me design for free. I went from business to business around my school area, offering free designs. I even designed my school handbook for free just to put myself out there. With this same skill, I met people I once admired from afar. I was willing to design for free just to earn a tag, a shout-out, and the visibility I desperately needed. There were times I slept in school just to use the school Wi-Fi to watch YouTube tutorials, especially from Mez Graphics. Sleeping in school became a lifestyle and it came at a cost. My health suffered deeply. I went through serious health crises because I couldn’t afford medication. Home was tough. Really tough. While others slept like humans, for four years in school I averaged two hours of sleep daily, juggling academics and survival. My health paid the price. I developed growths in both eyes that now require surgery, and my eyesight deteriorated so badly that I can’t function without my glasses. Yet today, this same skill has elevated my family. From living in a single room with five kids in a rented apartment, to my mum bring a landlord. A woman who used to fall sick frequently now lives healthier, eats whatever she wants, and glows differently. Poverty truly stinks but grace changed our story. The store she owns today? Courtesy of this skill and Web3. Every property I own my store, my home, everything came through design and Web3. This same skill funds my lifestyle. This same skill, backed by God, has elevated me beyond words. I could go on and on… This is me telling someone inspiring someone not to give up on that skill you have, no matter what it is, especially as a creative. I slept on YouTube for years because I couldn’t afford to pay for a single course. I used that knowledge to design for free sometimes for one, two, even three years just to build visibility. Today, I invest as much as ₦2 million yearly into learning., i invest heavily ngl If all you can afford right now is YouTube, be diligent with it. Mez Graphics and Caesar played huge roles in my journey, and I truly hope they see this. I am 100% grateful to them. In a nutshell: don’t give up on your skill. Keep refining it. Keep studying. Keep aspiring to be part of the top 1%. See you at the top If you read this far, thank you so much for reading 🫂show more

It’s 𝕏 payday. The day the world’s best creators... get paid for doing what they love. I now make more $ than I did during my 8 years at Apple. But to be honest, the $ is only small part of it. Today, I’m not tied to a desk. I don’t have a boss watching over me. No one is telling me where to be, what to work on, what to say, or what my day/life should look like. I wake up, bet on myself everyday, create and share my thoughts on what I believe in, and am doing something that really belongs to me. There is a MASSIVE premium on that kind of freedom that $ can’t buy. Once you experience it, it’s impossible to go back. The fulfillment and ownership of my own time cannot be replaced. I still remember everyone who told me I was stupid for wasting my time on 𝕏. “Get a real job.” “Those aren’t your real friends.” “No one cares what you post.” “Social media isn’t a career.” “You’ll never make real $ doing that.” “You just ride Elon’s dick.” “What you do isn’t even exciting.” “It won’t last.” Now all of those same people ask me how they can do it too. It’s really funny how betting on yourself looks foolish right up until it finally works. I built this life by showing up every single day when nobody believed in me and refusing to quit when it would have been easier to go back to Apple. I’m my own boss now. And I’m never handing that freedom back. 𝕏 is the place to be.show more

Stanford researchers did it again. They just built the... agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.show more

This Claude Code Skills Pack is a cheat code... for ad creative teams 🤯 10 plug-and-play skills → competitor audits, creative briefs, 20 hook variations, ad copy, static ads, landing pages, & weekly performance reports. All inside Claude Code. Perfect for DTC brands and agencies who are still prompting Claude Code from scratch every time. If you're re-explaining your brand voice in every session, getting inconsistent output depending on who's prompting, and spending 30 minutes on tasks that should take 30 seconds... These skills eliminate the entire loop: → Competitor Ad Research Agent Drop a brand name, get back a full creative audit — hooks, messaging angles, ad formats, CTAs, and "steal this" angles. No more scrolling the Ad Library for an hour. → Creative Brief Generator One prompt, complete brief in your exact template. Hooks, concepts, visual direction, brand voice — all loaded from your own files. → Hook & Script Writer 15+ hooks categorized by type (curiosity, problem-agitation, result-first, social proof). Full 30-60s scripts with the hook → problem → mechanism → proof → CTA structure baked in. → Ad Copy Variation Engine Feed it one winning ad, get back 20 variations — each targeting a different persona and pain point. Same structure, different angles. Creative fatigue solved. → Weekly Report Writer Drop in your Meta ads CSV. Get back the narrative summary, anomaly flags, creative fatigue alerts, and recommended next steps. The report nobody wants to write, written in 60 seconds. → Creative Fatigue Detector Flags ads before they die. CTR trending down, frequency climbing, conversion rate dropping — caught in hours, not after three days of wasted spend. No prompting from scratch every time. No inconsistent output across your team. No re-explaining context in every session. I packaged all 10 as a free Skills Pack. Copy-paste the files into your Claude Code commands folder and they just work. Want the full Skills Pack? > Like this post > Comment "SKILLS" And I'll send it over (must be following so I can DM)show more

YOUR GROK BOT HAS YOUR LOGINS AND ITS OWN... CLOUD COMPUTER. WITHOUT A RULEBOOK, IT WILL SPEND, POST, OR DELETE SOMETHING BY MONDAY THAT YOU CAN'T UNDO. saturday, 8am. i opened the laptop and started counting what a fresh bot had done overnight on the broad task i left him with. signed up for a paid trial in my name. replied to two DM. deleted a file it decided was clutter. none of it was catastrophic. all of it was mine to clean up on the weekend. the bot was doing exactly what i asked. i had just never told him what he was not allowed to do. so i wrote three files before the next task ran. 1. layer one: charter. one page in Bot actions, Description. name, who he reports to, what he owns, and the exact verbs he must park for me. send, publish, spend, delete, sign, sign-up. 2. layer two: rulebook. ten one-line rules he acknowledges before touching anything. rule 1 (if i cannot undo it in a minute, i park it) closed most of the friday-night damage. rule 9 (never paste a password, sign-in goes through the Agent Computer handoff) closed the rest. 3. layer three: routines. five saved jobs, not seven. morning brief at 7, weekly review on friday, end-of-day handoff at 6, silent-inbox catcher, monthly audit. anything else lives in me, not in the bot. the day after i pasted the three files, the same task came back with three parked questions and one finished deliverable. no signups. no DMs. no deletes. your bot is not scary because it is smart. it is scary because it has your credentials and no one told it what stop looks like. paste the charter and the ten rules before the next task runs. the routines can wait until the first parked question comes back the way you wanted.show more