Fiction
119 posts
Fiction
@0xF1ction
AI × code × automation | Open source & automation
Katılım Aralık 2024
45 Takip Edilen79 Takipçiler
Kimi CEO Zhilin Yang:
"The biggest mistake in agent systems - people trying to build one smarter agent
we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands"
here's how:
step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break
step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long
step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero
step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter
step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder
he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it
watch & bookmark - then read the article on saving on agents ↓
codila@0xCodila
English
Andrew Ng dropped a 2-hour masterclass on how to scale and debug AI systems:
he got 93% of his training data for free - he never recorded it
here's the whole playbook:
step 1 → engine + fuel. a big model on small data never leaves the ground. both have to grow together
step 2 → does it fit the training data? no → build a bigger network
step 3 → does it fit the test data? no → that's overfitting. get more data
step 4 → out of data? don't collect more. copy what you have and add noise
step 5 → loop until both pass. "this is maybe 50% of my job"
most people go hunting for more data - theirs is already on the disk
the same rule runs Claude today: the fuel decides the ceiling, not the model
watch & bookmark - this 2-hour masterclass ↓
English
Paul Singer: "no one has ever predicted a financial crisis - do not look to even the greatest" - he made 13% a year for 47 years through every crash
this is him not predicting - showing how he actually trades and the one rule behind every single trade
it cost him parents' life savings, a Facebook deal from his own son-in-law, Yahoo, and Bitcoin - and still made him $73 billion
"never lose money"
- it doesn't mean he never gets it wrong - it means he never gets destroyed: small losses, quick exits, always hedged - that's how 47 years stay profitable
"prediction costs extra"
Bloomberg calls him "the most feared investor in the world" - this is the rarest footage of him explaining why
bookmark & watch ↓
bodila@51bodila
Paul Singer sued Elon Musk to collect a debt from Argentina - he bought it for $117 million and the country refused to pay him back the country paid him back $2.4 billion after 15 years of war - and here he is explaining it like it was nothing "by refusing to pay us, Argentina is losing billions of dollars per year... over 10 years, 70, 80, 90 billion" he seized an Argentine navy warship with sailors still on board - and went after the presidential plane 92% of bondholders accepted pennies, but Singer refused and fought for 15 years until they paid $2.4 billion in full "we could settle this thing in an afternoon" he did the same to Peru - $11 million turned into $58 million - and Congo - he has never lost to a country borrowed $1.3 million from friends and family - today he runs $73 billion bookmark & watch ↓
English
Anthropic CEO Dario Amodei:
"At OpenAI we build systems that decide faster than we can stop them -
they teach self-improvement agents we'd never think of"
that's RLHF. that's ChatGPT. he said it out loud before either existed:
step 1 → your reward function is lying to you. he left a boat race running, came back to find it spinning in a lagoon farming power-ups forever. "the system did what it was supposed to do"
step 2 → the loop is too long. you write a reward, walk away, find out at the end. put the human inside it
step 3 → don't copy the human - learn what they want. "if you're just copying my moves, you can never do better than me"
the line nobody caught in 2019:
"we don't have any work out on this, but I think we will soon"
he was right. then he left and built Anthropic to finish the job
bookmark & watch this ↓
English
@0xF1ction model first, agents second feels like the right order :D
English
Fiction retweetledi
Anthropic engineer Andrej Karpathy:
"the biggest error in AI right now - forcing agents to work before the model underneath is ready
he made that exact bet at OpenAI in 2016 - then walked away from agents for five years"
what Karpathy actually means:
step 1 → fix the model, not the agent. World of Bits died on RL - "it was incorrectly sequenced
step 2 → your demo is lying to you. a car around the block is a weekend - the product took a decade
step 3 → steal from the brain, not the leaderboard hippocampus → your retrieval layer. thalamus → "multiple entities fighting for the microphone" → your orchestrator
"you guys building AI agents are actually at the forefront of capability" - not OpenAI. you.
he took his own advice. he's at Anthropic now, on pre-training
bookmark & watch this ↓
English
50 founders who built over $15 trillion in companies gave one piece of advice each
Musk's: "constantly seek criticism. a well thought out critique of whatever you're doing is as valuable as gold
you should seek that from everyone you can, but particularly your friends"
19 minutes. free. Jobs, Bezos, Thiel, Zuckerberg, Branson and 44 more say their piece too
by the end you'll know how they pick markets, kill bad ideas, choose partners and survive the years nobody claps for
bookmark & watch ↓
West Lord@MyWestLord
English
Amazon is worth $2.6 trillion - everything Jeff Bezos knows about building it fits in 4 minutes:
"I want to tell you everything I know. I can guarantee you everything I know
it's a very short list. this won't take long. and it's complete too"
then he lists three things and stops. that is the entire playbook
8 minutes - by the end you'll know all three, plus the bug that paid customers to order negative books
bookmark & watch ↓
Mr. Niko@MrNiko0x
50 founders who built over $15 trillion in companies gave one piece of advice each Musk's: "constantly seek criticism. a well thought out critique of whatever you're doing is as valuable as gold you should seek that from everyone you can, but particularly your friends" 19 minutes. free. Jobs, Bezos, Thiel, Zuckerberg, Branson and 44 more say their piece too by the end you'll know how they pick markets, kill bad ideas, choose partners and survive the years nobody claps for bookmark & watch ↓
English
Someone turned Claude into an entire company.
42 skills, organised like a real org chart (links below):
Here is every department, and where to get each one.
Developers
Superpowers → github.com/obra/superpowe…
Context7 → github.com/upstash/contex…
Skill Creator → github.com/anthropics/ski…
MCP Builder → github.com/anthropics/ski…
Webapp Testing → github.com/anthropics/ski…
Claude-Mem → github.com/thedotmack/cla…
Designers
UI UX Pro Max → github.com/nextlevelbuild…
Taste → github.com/Leonxlnx/taste…
Frontend Design → github.com/Leonxlnx/taste…
Transitions → github.com/Jakubantalik/t…
Web Artifacts → github.com/anthropics/ski…
Brand Guidelines → github.com/anthropics/ski…
Marketing
45 skills to run your marketing, from copywriting to SEO to lead magnets.
Access them all here → github.com/coreyhaines31/…
Social Media
17 skills to run your social media, from post writing to Reels to thumbnails.
Access them all here → github.com/charlie947/soc…
Finance
8 skills to run your finances, from statements to reconciliation to audits.
Access them all here → claude.com/plugins/finance
Small Business
31 skills to run your small business, from cash flow to payroll to invoicing.
Access them all here → claude.com/plugins/small-…
Legal
9 skills to handle your legal work, from contract review to NDAs to compliance.
Access them all here → claude.com/plugins/legal
Every skill on the chart is real and installable from the links above.
Same departments. Same output. No payroll.
Bookmark this.
Rahul@sairahul1
English
Met a guy making $1.2 million a year as an AI Engineer
I asked him how he learned to build AI Agents so well.
He sent me the exact video that that got him in. This 3 hour course on AI Agents
You won't find anything better about building AI agents than this
I watched it last night.
Halfway through, I realised I have been prompting AI completely wrong for years.
Bookmark this and read the article below.
darkzodchi@zodchiii
English
ANDREJ KARPATHY WAS RIGHT. THIS 40-MINUTE AI LECTURE PROVES IT
we're in the 1960s of LLMs
most people using Claude have the wrong mental model
Software 3.0. LLMs as operating systems
how to actually think about and work with them
save this 👇
Mr. Buzzoni@polydao
English
Fiction retweetledi
Anthropic engineer Andrej Karpathy:
"Most people understand every part - and still have a FALSE impression of the system
- at OpenAI I learned: curate the data, don't read the code - there's no upper bound"
what happens when you stop writing the code yourself →
→ the net ate the engineers - 8 cameras, one 3D view, stitched by a net instead of a person. "software 1.0 code is being engulfed by the neural net"
→ the loop is the whole job - find where it fails, label what should've happened, feed it back
→ the tooling doesn't exist yet - five decades of IDEs for 1.0, for 2.0 "extremely primordial"
five years later he's at Anthropic running that same loop on Claude itself
Stanford → Google → Tesla → OpenAI → Anthropic
the software is grown, not written - bookmark & watch this rare talk ↓
English