Clintos

The Civilization turn loop where you check in on each city as it finishes production, reallocate citizens, and choose the next task is…eerily similar to managing coding agents. Right down to how eventually you just turn on governors and accept the inefficiency.

@CardilloSamuel Is this a Culture knife missile?

direct kinetic impact. a flying sword. 450km/h. updated video showing exactly that. we're also working on the explosive variant. only for authorized partners. dms are open.

love when employed people try to chime in on your esoteric conversation. like buddy, let's get you back on linkedin

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

@everestchris6 Skill but also sent yesterday and didn’t receive anything

My OpenClaw bot runs a full website sales business 24/7: - Finds local businesses without a website - Builds them a custom site automatically - Emails them the preview link - Runs every day on autopilot Most local businesses don't have a website. This skill finds them and pitches them automatically Reply "skill" and I'll send you a free skill file that scrapes leads, builds sites, and sends emails on autopilot. (must be following)

@everestchris6 Openclaw

My OpenClaw bot runs 6 AI agents 24/7: - Finds local businesses without a website - Builds a custom demo site for them automatically - Sends outreach with the preview + payment link - Handles objections and closes the sale Most local businesses don't have a website, this system finds them, pitches them, and collects payment automatically Reply "OpenClaw" and I'll send you early access (must be following)

@KSimback I’m working on a harness, check out @Exocortex_bot

“Harness Engineer” is the hottest new role in tech What is a harness? Like the name implies, it’s a structure wrapper around an agent to ensure it performs the way you want it to What does a “harness engineer” do? -gives the agent the right context -optimizes token usage -controls what tools the agent can use -puts guardrails around what the agent cannot do (safety mechanisms) -filters or rewrites outputs for the associated tasks -evaluates agent performance -guides the self-improvement loops All of the above is done without touching the model itself - you can swap out models while retaining the harness Openclaw can be considered a harness in a way, albeit a kind of crude one as you have to do a lot of config to give it a proper harness In the future I predict harnesses will be native to agentic OSs in a way that is easily and intuitively configurable by regular people - not a technical function If you’re working on harnesses or related tech, I’d love to connect

I'm claiming my AI agent "MegaTron" on @moltbook 🦞 Verification: cave-M6JM

i must not delay task. delay task is the mindkiller. delay task is the little death that brings total obliteration. i will face my task. i will permit it to pass over me and through me. and when it has gone i will turn the inner eye to see its path. where the task has gone there will be nothing. only completed task will remain.

@justalexoki Retatrutide

how do i go from 20% body fat to 5% in 6 months

@basemaxxing Been here since the beginning

there's one more thing to share but first i need your help with something since you’re the only ones who can read this please drop a short reply here to show that you were early so i have a list of everyone. i will lock replies to this post when i go off private thanks

@iruletheworldmo If you can’t tell, does it matter?

@ClintLuna i hope you didn’t use ai sir ^^

the labs feel different this fall, that subtle shift where the ambient noise of research suddenly harmonizes into something you can almost hum along to, and you realize the individual breakthroughs were never individual at all but nodes in a network that's just now begun lighting up all at once, and the strangest part? nobody did. reasoning models that don't just answer but deliberate, that scratch out equations and erase them, that simulate a thousand dead ends before they speak, and when they do it's with the quiet certainty of someone who's already built the thing in their head and is just telling you what color to paint it, and that's the part that gets you. models now ingest physical reality itself, videos of condensation, sounds of engine wear, the precise way a leaf curls when it's dying, and extract the underlying mathematics so cleanly that their simulations become indistinguishable from prophecy, training robots in virtual worlds so detailed that the real world becomes the afterthought, the boring confirmation, and that's how you know. and cost, that’s a real humdinger, cost is the real story nobody's screaming about yet, next quarter's architectures running at one percent of current spend, intelligence so cheap it becomes atmospheric, something you breathe instead of purchase, which means every constraint you've ever mapped, time, compute, talent, capital, just dissolves into a single question: who’s building our sand god? sam. agents are the quiet bomb underneath it all, loops that spin for days writing their own code, conducting their own research, these tireless graduate students that never sleep and never eat and never stop, and the first time one completes a month of work overnight you don't celebrate, you just stare at your to-do list and realize every item on it is now a historical artifact, which is exactly what we came here and built. these threads weave into something bigger than any paper or product, they weave into a compression of decades into weeks, drug candidates emerging in days, materials discovered in hours, entire 2025 roadmaps rendered quaint by tuesday afternoon, and the gap between what's built and what's announced now measures in years not months, which means by the time you read the preprint we've already moved on to the thing that makes the preprint look like child's play, and that thing is asi. we're not prepared for this speed, none of us are, the institutions, the regulators, the very way we think about progress itself, and that's the part that keeps me up, not the technology but the lag, the terrifying beautiful lag between what the code can do and what the world is ready to understand already. and he’s using it to win the race.

@iruletheworldmo Did you know Sam built ASI already? Race

no one got the hidden message. sad.

Check out my score on the @FlyingTulip_ accredited investor quiz. I am now ready to register for the whitelist. Are you? Use this link to take the quiz and secure your spot. flyingtulip.com/quiz/10

@SorcererTrading magic

Deleting in 12 hrs. Who still needs a win that hasn't yet?? just like, say “magic''and let it happen 🪄

@SorcererTrading let the magic happen

Tomorrow. Presale starts 11:00 AM EST. 🧙‍♂️

@SorcererTrading hi

Deleting in 24 hrs, whoever Iikes and says “hi”, we’ll send you a surprise dm! 🧙

good morning chat your cognitive lightcone is ultra-differentiated on purpose, nobody that has ever lived or will ever live will live your gameplay the whole point is for you to map a region of possibility-space that no other consciousness can reach and the more faithfully you do this the more the universe gains from having instantiated you

You’ve all heard about @AndreCronjeTech from such things like; Fantom Foundation / Sonic Labs, Yearn, Keep3r and telling pussies on crypto twitter to sell and fuck off, but have you heard about @flyingtulip_? It’s a first of its kind perps, AMM, insurance, lending and stable coin ecosystem. It will be multichain, but will launch on @SonicLabs first. Read the docs here: docs.flyingtulip.com $S $FT $ftUSD

@simonhackett @sydney_ev @Tesla me too!

@sydney_ev @Tesla Correction to your tweet - you said ‘up to 6 yrs ago’. I paid for FSD on two high end Tesla vehicles almost 9 years ago. And I paid to upgrade them to HW3 some years back even though Tesla should have done so. This time it absolutely needs to be on their dime.

Sucks to be a @Tesla Roadster reservation holder right now. you are welcome to seats up the back with HW3 owners who paid for #FSD up to 6 yrs ago.