New results! The prefrontal cortex uses a low-dimensional “coding space”. Info can be captured in just 3–6 dimensions. The brain compresses what we remember.
Low-dimensional prefrontal representations of objects during working memory
https://t.co/kUONPmdNnD
#neuroscience
I've been coding for 40 years. Here are the top 5 things I wish I knew when I started.
1. 90% of the job is debugging and fixing, not creating new code. Which is still fun if you're good at it.
I used to think programming was mostly writing fresh, clever stuff. In reality, most of your time is spent in other people's (or your own past self's) messy code, chasing down why something that "should" work doesn't. Get really good at debugging early. Learn assembly reading, call stacks, and kernel debuggers. It pays off hugely. The best engineers I saw were absolute magicians at this.
2. Manage complexity from day one (ie: don't write slop and "fix it later" if it goes somewhere).
Very early on, I'd hammer out code and refactor afterward. Big mistake. Now I start with clean, skeletal structure (minimalism first) and flesh it out carefully, with AI or not.
Messy code compounds and becomes unfixable. Upfront discipline on architecture, naming, and simplicity saves enormous pain later, especially in large systems like Windows.
3. Tools and processes matter more than you think
We suffered with basic diff/manual deltas instead of modern source control like Git. Branching, testing, and good tooling would have made porting and collaboration way smoother. Invest in your environment, automation, and reproducible builds early. Good tools amplify your output; bad ones (or none) drag everything down.
4. Understand the problem and existing code deeply before writing
Don't jump straight to coding. Map out the problem, study what's already there (you'll inherit a lot), and plan. Low-level knowledge (hardware quirks, alignment issues on different architectures like MIPS/Alpha) was crucial. Also: assert early and often. It forces clarity.
5. People, politics, and "the right tool for the job" beat pure tech arguments.
Brilliant engineers still argue endlessly. Sometimes it's about ego, not merit. Learn to spot the difference and "steer" the conversation rather than "winning" it.
Bonus from experience: Side projects like Task Manager (started at home because I wanted the tool) can become your biggest hits. Ship small, useful things often. If you're just starting, focus on fundamentals, patterns over syntax, and building resilience for the long haul. It's going to be a wild ride, but the fundamentals still matter.
Jeff Bezos is funding scientists who are reprogramming organs outside the human body.
Altos Labs removes the organ. Keeps it alive on a machine. Then runs rejuvenation therapy on it directly.
No patient risk. No waiting. Just a living organ, isolated, and reset.
It sidesteps the biggest problem in aging science: you can't easily test reversal therapies on humans without first knowing they're safe.
A perfused organ solves that.
$3 billion raised. Bezos in. The experiments are running now.
The body may be optional for what comes next.
People who are usually private and reserved, even with their friends, end up sharing all manner of personal details on a long flight with a stranger they will never meet again.
I’ve come to the conclusion that those who are pushing agentic systems have at least three glaring holes in their approaches:
Most are entirely ignorant of the existing literature in this space, both from early AI to biological studies of swarms to complex systems theory. This is not a new landscape.
Orchestration among agents is either treated as an afterthought or via extremely naive centralized architectures. This BTW is why I am a fan of blackboard architectures as pioneered in Hearsay years ago and in @BernardJBaars global workspace theory.
There exist many flavors of agents and yet most today are a little more than trivial input/output mappings.
This is fertile ground, but most are planting seeds opportunistically in fallow ground, without consideration for where they may fall or how they may be nourished.
RAG is broken and nobody's talking about it.
Stanford researchers exposed the fatal flaw killing every "AI that reads your docs" product in existence.
It’s called "Semantic Collapse," and it happens the second your knowledge base hits critical mass. If you've noticed your AI getting "dumber" as you add more data, this is exactly why.
Right now, companies are dumping thousands of documents into their AI, thinking it’s getting smarter.
When you add a document to RAG, it converts it into a high-dimensional vector.
Under 10,000 documents, this works perfectly. Similar concepts cluster together.
But past 10,000 documents, the space fills up. The clusters overlap. The distances compress.
Everything starts to look "relevant."
It is a mathematical law called the Curse of Dimensionality. In a 1000-dimensional space, 99.9% of your data lives on the outer edge. All points become equidistant from each other.
That perfect, relevant document you are looking for now has the exact same mathematical similarity as 50 completely irrelevant ones.
The Stanford findings are brutal:
At 50,000 documents, precision drops by 87%. Semantic search actually becomes worse than old-school keyword search.
Adding more context doesn’t fix the AI. It makes the hallucinations worse.
Your "nearest neighbor" search isn't finding the best answer anymore. It's finding everyone.
We thought RAG solved hallucinations.
It didn't. It just hid them behind math.
@godofprompt Sounds a lot like @Kasparov63 who at the time was the greatest chessplayer alive, claiming that:
centaurs = human + computer > either
That turned out to be true for maybe 7 years. Now computer alone without human in the loop is way more dominant.
That’s what is coming…
This 16-min lecture on "Black Scholes model" by Nassim Taleb will tell you more about quant trading than a 2 month internship at Goldman Sachs or JPMorgan.
Bookmark it & watch today,no matter what. It’s the most productive way to start your week. Then read article below.
Jesse Genet on Agentic Parenting
Jesse Genet joins a16z's Sarah Wang and Katherine Boyle to discuss her journey from founder to parent, how she's using agents in her household, and how AI could transform parenting for the better.
00:00 YC founder turned homeschool mom
03:00 Discovering Claude Code and agentic building
06:00 Building while homeschooling 4 kids under 5
11:00 How AI generates personalized lesson plans and logs progress
18:00 Jesse's 11-agents
27:05 Agent tech stack deep dive
33:56 How agents improve daily life
40:04 Letting kids interact with AI: values, risks, and the future of parenting
@jessegenet@KTmBoyle@sarahdingwang
this parent is using 11 openclaw agents to raise her kids
ironically it’s the most effective ai agent setup i’ve seen:
- the agents home-school her kids. she takes a picture of a curriculum, agent creates a personalised lesson plan, teaches kids, tracks progress
- voice-only. she leaves agents voice notes to do her job (code), order groceries etc
- agents schedule “ignore kids” time for her to let them be bored
- agents run on several mac minis, do all the house admin and free up her time
i know this sounds dystopian af but tbh if used correctly this could do the opposite and free you up to hang with the kids
i think the scheduled ignore time it a little much tho
someone built an OpenClaw agent that SELLS pool installations on autopilot.
finds $500k–$1.2M homes without pools
renders a pool in their backyard
and mails a before/after postcard.
Cancer is cured by AI.
GitLab founder Sid Sijbrandij was diagnosed with stage 4 spinal cancer. Every trial rejected him.
His doctors had nothing left to offer.
So he stopped being a patient.
He built an AI research team. Fed them 25TB of his own medical data genomics, scans, treatment history, everything.
The system found a treatment his entire oncology team had missed.
Then engineered 19 custom vaccines from his own DNA.
Relapse-free since 2025.
Then he uploaded the entire blueprint. Free. For every person sitting in that same room, hearing the same verdict, with nobody left to call.
Medicine runs on averages. AI runs on you.