Bookmarked from Andrew Côté @Andercot
A realistic picture of how closely packed molecules are inside a synapse of a nerve cell.
@trq212 Hey man, what I want to understand is, if I am going to be banned using my MAX sub for openclaw or not
5632 bookmarks · page 22 of 226
A realistic picture of how closely packed molecules are inside a synapse of a nerve cell.
@trq212 Hey man, what I want to understand is, if I am going to be banned using my MAX sub for openclaw or not
The funniest take is that I "failed" 43 times when people look at my GitHub repos and projects.
Uhmm... no? Most of these are part of @openclaw, I had to build an army to make it useful.
The thing with a lot of white collar work is that the thinking/talking is often the majority of the work… unlike coding, where thinking is (or, used to be, pre-agent) a smaller percentage of the time consumed. Writing the software, which is essentially working through how to implement the thought, used to take a much larger percentage of the overall time consumed from thought to completion.
Other white collar business/bullshit job (ala Graeber) work is meeting with people, “aligning expectations”, getting consensus, making slides/decks to communicate those thoughts, thinking about market positioning, etc.
Maybe tools like Cowork can help to find files, identify tickets, pull in information, write Excel formulas, etc.
What’s different about coding is no one actually cares about code as output from a business standpoint. The code is the end destination for decided business processes. I think, for that reason, that code is uniquely well adapted to LLM takeover.
But I’m not so sure about other white-collar jobs. If anything, AI tooling just makes everyone move faster. But an LLM automating a new feature release and drafting a press release and hopping on a sales call to sell the product is (IMO) further off than turning a detailed prompt into a fully functional codebase autonomously.
My compsci brain suggests large orgs are a distributed system running on faulty hardware (humans) with high network latency (communication). The individual people (CPUs) are plenty fast, we just waste time in meetings, or waiting for approval, or a lot of tasks can't be parallelized, etc. Before upgrading, you need to know if you're I/O Bound vs CPU Bound.
remarkably beautiful to see this type of a candid video for a product that is now so ingrained into culture that there is not one person on the planet who hasn’t heard of it.
almost as if it was ordained by god to exist.
Psilocybin appears to simultaneously be an anti-depressant / quality of life enhancer, anti-addiction drug, neuroplasticity booster, and a plausible longevity drug.
Running NanoClaw in a Docker Shell Sandbox (docker.com)
And there lies the trap! 😂
It's because there isn't any proper auto-compacting for sessions.
Thus, if you create a tool in a session it is logged both to your
~/.openclaw/agents/main/sessions/sessions.json
AND will be linked as context via your current session's ~/.openclaw/agents/main/sessions/[UUID].jsonl
file - both of which are sent as context to the LLM inference API as context of the current chat/request.
So a simple, 'Hey' can actually contain the full build of your tool, and modifications of it, edits, uses, chats and versions and revisions of it, logged uses of it, + the session file + 'Hey'
= shedload of tokens!
Workarounds for building tools and in general:
1) Always use a subagent - just ask it to:
"use another agent to [do X,] and when done add it to 'memory' "
and it will be in a session file outside the main one,
1b) (make sure you have the memories skill enabled!)
2) When working on it for a while, and when done - before finishing the session use:
/compact slash command
to keep the tokens controlled, so even if it is referenced in the future it has been pruned.
3) When finished, run /new to clear the session/tokens and start out with just the base context/memories/last pruned session as context.
After a while though even memories etc can build up, that's when using lots of individual agents comes into it, the main agent becomes the orchestrator and only sends the relevant request and relevant context needed for it per task to the sub-agent.
Focus on the product, 0 sales
Focus on their problems, 100 sales.
That's the game.
Ever wondered why OpenClaw went viral but many other similar projects didn’t?
Well, just look at the number of projects by OpenClaw’s creator.
Virality is a function of number of attempts. It’s so rare and unpredictable that your best bet is to maximize taking shots at it.
Same is true with tweets/videos. You’d see that the fastest growing accounts are those that produce a ton, and not those that keep perfecting a single thing that they hope to go viral.
the best posts on here land like a punch to the gut or a warm hug. ppl don’t tend to remember what was smart. they remember what felt real.
pain, love, joy, loss... this is the stuff every human recognizes instantly.
the best writing drags someone into your world & makes them live there for a minute. & when you write from a place that clearly cost you something, people read it like: “oh. this person isn’t performing. they’re actually bleeding.”
how many users do you need before implementing a staging branch?
@danielrakh @bengold Engineers, 2 designers, 1.5 product managers and me
New art project.
Train and inference GPT in 243 lines of pure, dependency-free Python. This is the full algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further.
Prediction: In less than 90 days, all channels that we thought were safe from spam & automation will be so flooded that they will no longer be usable in any functional sense: iMessage, phone calls, Gmail.
And we will have no way to stop it.
Free startup idea:
Train a Foundation Model, only on raw binary.
Since the vocab size is strictly just 0 and 1, you only need 2 trainable parameters,
Not 2 billion. 2.
It would be super-lightweight, and knows how to generate every piece of software ever created $$$ 👀
i gave an AI $50 and told it "pay for yourself or you die"
48 hours later it turned $50 into $2,980
and it's still alive
autonomous trading agent on polymarket
every 10 minutes it:
→ scans 500-1000 markets
→ builds fair value estimate with claude
→ finds mispricing > 8%
→ calculates position size (kelly criterion, max 6% bankroll)
→ executes
→ pays its own API bill from profits
if balance hits $0, the agent dies
so it learned to survive
built in rust for speed
claude API for reasoning (agent pays for its own inference)
runs on a $4.5/month VPS
weather markets: parses NOAA before polymarket updates sports: scrapes injury reports, finds mispricing crypto: on-chain metrics + sentiment
$50 → $2,980 in 48 hours
how much do u think i’ll see in a week?
Magic mushrooms did a 'force quit' to my thought patterns. Nothing else has done that before.
Kindness is peak human performance and high status.
Kindness requires metabolic abundance: the capacity to override primal impulses, regulate emotions, and extend empathy.
Meanness is dirty energy: high cortisol, inflammation and an exhausted executive function.
The dog likes it so much when I spill food on the floor when I'm cooking that I usually spill a little on purpose. So now I can't cook without constantly tripping over the dog.
App Store screenshots I delivered in January
A pretty productive month 🔥
Grateful to all my clients for their trust 🙏
This was a book recommended to me by an experienced remote viewer. The author Dr. Moorhouse was one of the original U.S. Army Intelligence Stargate participants. The perfect book for anyone wanting to learn the U.S. military approach to remote viewing: amazon.com/Remote-Viewing… #ad
This app is making 250k installs monthly and an MRR of $350k!
But How?
90% of users goal six months later → a statistic that builds trust
learn on your own with AI → more confidence and more downloads
all app's features for free → gives value before purchase ⬇️