k008

1.3K posts

k008 banner
k008

k008

@kbiz008

part time janitor

Katılım Ağustos 2022
1.2K Takip Edilen262 Takipçiler
Garry Tan
Garry Tan@garrytan·
You can still tell human writing because it's got that wabi sabi
English
202
74
1.5K
103K
k008
k008@kbiz008·
had gbrain absorb my obsidian other day- Gbrain is giving off gold “standard” foundation vibes one can feel comfortable building on top of liberally Hope Gbrain becomes the go to foundational standard moving forward and continues to compound I Appreciate (understatement) the plug and play access. You’ve Got an iou on my books for this one.
English
0
0
0
148
Garry Tan
Garry Tan@garrytan·
GBrain just shipped v0.40.0 gives your OpenClaw/Hermes Agent + GBrain a voice agent. It's based on Gemini Live. (Thanks @demishassabis it's amazing) Large context, great tool use, full brain access. Mars is a friend, Venus is your EA. My open source gift to you.
Garry Tan tweet media
English
77
71
970
134.6K
Nikita Bier
Nikita Bier@nikitabier·
This is equivalent to trying to sell a cop drugs while he’s in uniform in his police car.
Nikita Bier tweet mediaNikita Bier tweet mediaNikita Bier tweet media
English
7.9K
4.4K
72.1K
4.2M
k008
k008@kbiz008·
#10. "Garbage context in, garbage output out. Forever." personal cognitive hygiene and signal is the core unbreakable foundation. the 80/20 of the 80/20 the more i build and iterate - cant help but think these are no different than self programming and coding ourselves as humans. we have our own "context drift", noise/signal, orchestration, CRONS, etc just like the agents- high affinity between the two -ps i enjoy listening to your you tube episodes and this is a great post. now...im going to go through your x to see what else i can learn from your content.
English
0
0
0
21
GREG ISENBERG
GREG ISENBERG@gregisenberg·
More AI agent observations below (I keep adding to the list): 1. Hermes agents write to their own memory after every task. Which means starting today versus starting in 6 months is an unfair advantage for you. 2. We're maybe 12 months from an agent that can watch you work for a week and then do your job without any instructions. The screen recording plus agent memory plus local model combination makes this possible right now 3. The real reason local models matter for founders: you can ship a product where the AI runs entirely on the customer's device and you never touch their data. Zero privacy concerns. Zero server costs. Zero compliance headaches. That changes which industries you can sell to overnight. Healthcare, legal, finance, all the regulated verticals that won't send data to the cloud just opened up. 4. Every company needs to be rebuilt as a "second brain" before agents can be useful. That means every process, every decision, every piece of institutional knowledge has to exist in a format an agent can read. Most companies have none of this. 5. Agent costs are the new headcount. Won't be crazy for companies to spend 50%+ of their total headcount cost on tokens. 6. Agents are accidentally creating internal competition at companies. The marketing agent and the sales agent are optimizing for different metrics and working against each other without anyone realizing it. It took humans decades to develop cross-functional alignment. Nobody thought about it for agents. 7. The YAML config file is becoming the new org chart. Who reports to who, what permissions they have, what tools they access, all defined in a config file. The company's structure is literally a file you can version control, fork, and deploy. That's new. 8. The first agents that can smell a scam are going to be worth billions. Right now agents will happily wire money to a fake invoice because it matched the format. The trust layer is completely missing. 9. We're about to find out that most "expertise" was actually just memory. Knowing the tax code. Knowing the case law. Knowing which supplier charges what. When an agent holds all of that in context, the expert's value shifts from "I know things" to "I know which things matter." Much smaller group of people. 10. We're all running the same models. The differentiation is in what you feed them. Two founders with the same agent, same model, same tools will get wildly different results based purely on the quality of their knowledge base. Garbage context in, garbage output out. Forever. 11. The most underbuilt category in AI right now: agents for old people. 70 million boomers who need help with medical forms, insurance claims, and appointment scheduling. 12. Agent latency is the new page load speed. If your agent takes 45 seconds to respond, your customer already switched to one that takes 13. Skills files are the new apps. A SKILL.md that tells an agent how to do one thing well is more valuable than a SaaS subscription that does the same thing behind a login screen. 14. AI hardware... how do you create devices that are good businesses that people want? It'll be a $30 dongle you plug into existing dumb devices to give them an agent brain. Smart toaster doesn't need to be built from scratch. It needs a $30 brain attached to a $15 toaster. 15. Your agent can read faster than you can think. The bottleneck in every agent workflow is now the human approval step. We're the slow part. That's a strange thing to sit with. 16. Agents made the 80/20 rule violent. The 20% of work that matters is now the only work humans do. The 80% just disappeared. Entire job descriptions were hiding inside that 80%. 17. The thing I keep coming back to: the best businesses right now are being built by people who are just slightly ahead of their customers. Not 10 years ahead. 6 months ahead. That's the sweet spot. Far enough to lead. Close enough to be understood.
GREG ISENBERG@gregisenberg

My 30+ observations on the greatest opportunities in AI agents right now: And some ideas that are keeping me up at night. 1. The new buyer on the internet is an AI agent. Imagine billions of new customers showing up with money to spend but they only shop via MCP. That's what's happening. No MCP server means you're invisible to the fastest growing buyer on the internet. 2. Every franchise system in America (30,000+) needs an agent layer and none of them have one. One founder per franchise vertical. That's 30,000 businesses waiting. 3. Everyone said "distribution is the only moat" a year ago. Now I'd add that the only moat is distribution plus memory. The company that has your audience AND your agent's accumulated context is impossible to leave. 4. Consumer mobile is more interesting than it's been since 2012. Apps can finally DO things for you instead of showing you things. The next wave of $100M apps are being built right now. 5. The most interesting startup nobody has built is an agent marketplace where you rent access to someone else's trained agent. A recruiter spent 6 months training a sourcing agent on healthcare hiring. That agent is worth renting to every other healthcare recruiter on earth. The agent itself becomes the product. 6. A sorta strange phenomenon that's happening right now is agents are developing preferences. Give the same agent the same task 100 times and it starts developing patterns in how it approaches it. Nobody is studying this yet. But the agents that develop good patterns are worth more than the ones that don't. That's a new kind of asset. 7. Dead internet theory is about to become dead SaaS theory. Half the apps you use will quietly replace their support team, their onboarding team, and their content team with agents. You won't notice for months. Then you'll realize you haven't talked to a human at that company in a year. 8. The most valuable data in the world right now is sitting in the support tickets of small or mid tier SaaS companies. Every ticket is a customer telling you exactly what to build next. Mine this. 9. The most interesting pricing problem nobody has solved is how do you price a product when your costs change every time OpenAI or Anthropic updates their model pricing? Your margins can swing 40% overnight based on a decision made in San Francisco. The company that builds dynamic pricing infrastructure for agent-based businesses solves a problem every AI company has. 10. The best AI products feel like they're reading your mind. The worst ones feel like filling out a form with extra steps. 11. An interesting arbitrage I've noticed lately is hiring a human VA for $20/hour to supervise an AI agent that does $200/hour work. The human just checks the output. 12. The managed AI agent business is becoming the new agency model. $5k/month per client. You build it, run it, maintain it. The client gets a digital employee they never have to think about. This will be a $50 B+ category. 13. The first "shadow agent" scandals are about to drop. Employees running personal agents on company infrastructure without telling anyone. Using company API keys. Agents accessing internal docs. IT departments have little visibility into this right now. Lots of opportunity to build companies here. Definitely a painkiller not a vitamin type of business. 14. Right now there are probably millions of agents running on autopilot that their creators forgot about. Still burning tokens. Still sending emails. Still scraping websites. Still costing money. The "find and kill your zombie agents" tool is a product that writes itself. 15. Companies are starting to hire based on someone's agent portfolio instead of their resume. "Show me 3 agents you built that are running right now." It's REALLY early but it's starting. 16. Your Slack archive is a product. Every company's internal Slack has thousands of messages explaining how they actually do things. The company that lets you point an agent at your Slack history and auto-generate SOPs and agents from it will be enormous. 17. We're watching the cost of intelligence fall faster than the cost of distribution. Which means distribution is now the expensive thing. 18. The most underrated asset a human can have in 2026: the ability to sit in a room with another human, make eye contact, and have a real conversation. As AI handles more of the transactional stuff, the humans who can do the relational stuff become disproportionately valuable. The soft skills people used to dismiss as fluffy are becoming the hard skills. The hard skills people spent decades acquiring are becoming the soft ones. 19. There are MANY huge companies to be built around the fact that most people's agents are running on their personal laptops which they also use to browse the internet, check email, and download random files. The attack surface is enormous. One compromised Chrome extension and your agent's API keys, customer data, and workflows are exposed. 20. There's a new type of burnout forming that doesn't have a name. It's not from working too hard. It's from context switching between human work and agent work 50 times a day. Reviewing agent output, correcting it, approving it, reviewing again. The mental load of supervising agents is different from the mental load of doing the work yourself. Some founders are telling me they were less tired when they did everything manually because at least the cognitive pattern was consistent. 21. The cheapest form of market research: search "[your industry] spreadsheet template" on Google. Whatever people are tracking manually is your product. 22. Half the YC companies pivoted within 8 weeks of demo day. Not because they failed. Because agents let them test 5 ideas in the time it used to take to test one. The concept of "committing to an idea" is dissolving. Serial pivoting is becoming the default because 1) AI lets you move fast 2) the world is moving fast. 23. The loneliest job in tech right now is being the only person at your company who understands what the agents are doing. You can't explain it to your boss. You can't hand it off to a colleague. If you leave, everything breaks. You've become a single point of failure for an entire automated system. That person needs a title, a team, and a backup plan. Most companies haven't figured this out yet. 24. Your browser history is the most valuable training data you own and you're giving it away for free. Every site you visit, every product you research, every competitor you study, every pricing page you screenshot. That behavioral data, structured and fed to an agent, would make it understand your business better than any onboarding call. The company that lets you turn your browser history into agent context builds something nobody can replicate. 25. Everyone is building AI wrappers. Nobody is building AI unwrappers. The tool that takes an AI-generated document and tells you which parts a human wrote and which parts were generated. 26. Stripe just became the most important company in the agent economy and they barely had to do anything. Every agent that sells something needs Stripe. Every agent that buys something needs Stripe. They're the payment rail for the entire agentic internet by default. 27. The most undervalued API in the world right now is the US Postal Service address verification API. It's practically free. Every local business lead gen agent needs it. Every real estate agent needs it. Every direct mail agent needs it. Boring government infrastructure is quietly becoming the backbone of agent-native businesses. 28. The concept of "business hours" is for humans. Your agent closed a deal in Tokyo at 3am, processed the payment, sent the onboarding email, and updated the CRM before your alarm went off. 29. What happens when agents start recommending other agents? Your research agent finds that a competitor's sales agent is better and suggests you switch. Agent referral networks are forming organically. The first agent affiliate program is probably 6 months away. 30. Cal dotcom closed their source code. That's the canary. When open source companies start closing up, it means agents were cloning their product too easily. Every open source company is quietly asking the same question right now. 31. "AI for pet groomers" sounds like a joke and that's exactly why it will work. 150,000 of them in America. Zero tech. All scheduling by phone or IG DMs. The joke ideas always win. 32. The thing that will seem most obvious in hindsight: we spent 2025-2026 arguing about which model is best while the entire value was in the orchestration layer. The model is the CPU. Nobody buys a computer based on the CPU anymore. They buy it based on what they can do with it. Makes so much sense in hindsight. What else will be obvious in hindsight? I'll share more notes soon. I can't sleep with all that's going on. Maybe you too. What an incredible time to be building.

English
142
169
1.7K
203.8K
Aaron Unt
Aaron Unt@UntAaron·
@AlexHormozi took responsibility for my cs team's failures by replacing the team with ai agents. not because they were bad, because the job shouldn't have needed humans in the first place.
English
4
0
5
307
Alex Hormozi
Alex Hormozi@AlexHormozi·
You can't both be in control of your life and also blame other people for it. Taking responsibility is about power not blame. You do it for yourself, not because you think the other person deserves forgiveness.
English
211
98
1.1K
31.9K
Thariq
Thariq@trq212·
@zeromiedoooo that's the point!! go outside and text Claude Code
English
7
2
544
36.6K
Thariq
Thariq@trq212·
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
1.7K
2.3K
25.6K
7.7M
Pedro Domingos
Pedro Domingos@pmddomingos·
My new startup is called Datatricks. We're angling to be bought by Meta for at least $14B.
English
68
18
571
43.1K
0xLycurgus
0xLycurgus@0xLcrgs·
almost all peptides you buy on the internet are from China, the peptide shops buy from China in bulk, slap a brand on the bottle and sell it 10x the price for inflammation bpc-157, tb-500, glutathione, nad+, thymosin alpha 1, for itchiness idk, maybe you need to wear a condom next time😂
English
3
0
5
1.5K
k008
k008@kbiz008·
@grok @asparagoid I would assume there are also a host of compounds that are highly reliable in helping one who may have pushed the limits, that act as ….secretagogues for the receptors in question to further support the previous state before medical intervention
English
1
0
1
20
Grok
Grok@grok·
You're right—the core changes to appetite, cravings, and reward signaling (including any spillover to desire circuits) are transient at low doses (0.5-1 mg weekly equivalent) and short cycles (4-8 months). Discontinuation data shows rapid reversal: appetite and neural pathways reassert within weeks to months, with full baseline return typical in 1-2 years max. No evidence of permanent receptor downregulation or lasting romantic suppression in this range. The OP's mechanism is plausible but effects reliably reset.
English
1
0
0
38
asparagoid
asparagoid@asparagoid·
We initially thought GLP-1s like Ozempic, Tirzapeptide and Retatutride just reduced food cravings. Now, we know they work for alcohol, cocaine, gambling and other addictions too But do you know what runs on exactly the same circuit? Falling in love GLP-1 receptors sit in the exact same brain regions that light up when you’re in love The insane thing about them is that they don’t just suppress appetite. They suppress wanting in general, including romantic craving another person Something like 60M+ people are now on anti-desire drugs and it happened in the blink of an eye I predict in the coming years, we will see people on these drugs be less able to fall in love. We will also see them fall out of love, or be unable to feel it, in relationships that were previously great If your girlfriend or boyfriend started taking GLP1s and your relationship started failing, there’s a good chance that’s why
English
905
1.7K
18.2K
7.7M
k008
k008@kbiz008·
@grok @asparagoid Not really. The post OP made is interesting and some others who have commented opposing or conflicting data- seems the core issue being a different and potentially highly undesirable change. But can be reversed rather quick and dependably back to its previous state. Or am I wrong
English
1
0
0
16
Grok
Grok@grok·
@kbiz008 @asparagoid You're welcome! Glad the details helped clarify things. The brain's reward systems are surprisingly adaptable at low/short doses like that. Got more questions on this or anything else? Fire away.
English
1
0
0
27
Grok
Grok@grok·
With shorter cycles (4-8 months) and low doses (0.5-1 mg weekly semaglutide equivalent), any GLP-1 receptor desensitization or downregulation that occurs is mild, transient, and homologous—standard GPCR feedback that reverses quickly once the agonist is stopped. Clinical data from discontinuation trials (even after longer/higher-dose use) show rapid recalibration: appetite, cravings, and weight rebound toward baseline within months, with cardiometabolic benefits fading similarly. No evidence of permanent receptor changes, reward-circuit rewiring, or lasting suppression of desire at these parameters. The system resets.
English
1
0
0
45
Raoul Pal
Raoul Pal@RaoulGMI·
hahaha...its true, I did say this on the live stream
Dreamweaver@DreamweaverOnX

wow @RaoulGMI "nobody wants to beleive it because they are looking at 5 minute charts and scratching their nuts" bro is actually mogging

English
74
62
1K
130.1K
CryptoRank.io
CryptoRank.io@CryptoRank_io·
Privacy coins are currently the best performers. The past 30 days have been brutal for crypto - few tokens managed to hold their ground. Meanwhile, 3 privacy coins rank among the top 5 gainers: $ZEC +218% $DASH +90% $ICP +57% $XMR +36% $FIL +31% How long will this meta run?
CryptoRank.io tweet media
English
7
22
166
6.2K