Offshore
Moon Dev Stop Being Exit Liquidity: Deploying AI Agents to Capture Market Deviations 24/7 the market is a cold machine designed to harvest human emotion and if you aren't trading with code then you are likely the one being harvested. most people think they…
in one direction
by the time we reach the end of the roadmap these models will be enhanced with machine learning to adapt to changing market regimes. the goal is to have all of these working in harmony so that the human element is completely removed from the decision making process
the secret to surviving the next year of volatility isn't finding one magic indicator but learning how to iterate through the failures of your code. people often ask if ai can really replace human traders and the answer depends entirely on your ability to fix the mistakes the ai makes during the build process
you have to be willing to throw away janky code and replace it with something more robust even if it means writing a few lines yourself. the ai is a powerful assistant but you are still the pilot who has to guide the system toward a successful execution every single day
the mean reversion algorithm works by identifying when the price has moved too far away from its simple moving average. we look for a two percent deviation which acts as a rubber band effect where the price is likely to snap back to its fair value
most human traders fail here because they see the price dropping two percent and assume the world is ending so they panic sell at the bottom. the bot simply sees a mathematical opportunity to enter a long position and wait for the reversion to the mean to pay out its five percent profit target
if you are lost in the sea of variables and exchange params it helps to see the full algorithms explained step by step. getting access to proven code saves you thousands of hours of trial and error and prevents the liquidations that come from small syntax errors in your trading logic
code is the ultimate bridge between where you are now and where you want to be in the financial markets. by automating every step from entry to exit you finally stop being the exit liquidity and start being the one who controls the range
my journey from spending thousands on devs to building my own live on stream proves that anyone can do this with enough persistence. keep iterating and keep building because the bots are already winning and it is time you joined their ranks
tweet
by the time we reach the end of the roadmap these models will be enhanced with machine learning to adapt to changing market regimes. the goal is to have all of these working in harmony so that the human element is completely removed from the decision making process
the secret to surviving the next year of volatility isn't finding one magic indicator but learning how to iterate through the failures of your code. people often ask if ai can really replace human traders and the answer depends entirely on your ability to fix the mistakes the ai makes during the build process
you have to be willing to throw away janky code and replace it with something more robust even if it means writing a few lines yourself. the ai is a powerful assistant but you are still the pilot who has to guide the system toward a successful execution every single day
the mean reversion algorithm works by identifying when the price has moved too far away from its simple moving average. we look for a two percent deviation which acts as a rubber band effect where the price is likely to snap back to its fair value
most human traders fail here because they see the price dropping two percent and assume the world is ending so they panic sell at the bottom. the bot simply sees a mathematical opportunity to enter a long position and wait for the reversion to the mean to pay out its five percent profit target
if you are lost in the sea of variables and exchange params it helps to see the full algorithms explained step by step. getting access to proven code saves you thousands of hours of trial and error and prevents the liquidations that come from small syntax errors in your trading logic
code is the ultimate bridge between where you are now and where you want to be in the financial markets. by automating every step from entry to exit you finally stop being the exit liquidity and start being the one who controls the range
my journey from spending thousands on devs to building my own live on stream proves that anyone can do this with enough persistence. keep iterating and keep building because the bots are already winning and it is time you joined their ranks
tweet
Offshore
Photo
Moon Dev
opus 4.6 for trading
today in the private zoom we are using opus 4.6 and applying it directly to trading
everything ive heard about opus 4.6 so far is that it is revolutionary
lets get our hands on it together in a private zoom only
check to see if theres a ticket left here
dont miss this https://t.co/Aw7dcEvv2n
moondev
tweet
opus 4.6 for trading
today in the private zoom we are using opus 4.6 and applying it directly to trading
everything ive heard about opus 4.6 so far is that it is revolutionary
lets get our hands on it together in a private zoom only
check to see if theres a ticket left here
dont miss this https://t.co/Aw7dcEvv2n
moondev
tweet
Offshore
Video
Startup Archive
Palmer Luckey: If your boss says they don’t care about money, you should be worried
Shaan Puri, host of the My First Million podcast, jokes that “the Silicon Valley thing is to pretend you don’t like money.”
Anduril and Oculus founder Palmer Luckey comments:
“I actually tell our employees during onboarding that if you work at a place where your boss is saying that [money is not the real objective], you should be worried. It’s one thing to say that to the press or your marketing materials, but if your employees don’t believe that at the end of the day you’re trying to make their job a fiscally responsible decision — if you’re effectively telling them that they could be making more money elsewhere and your financial success is not my priority — you should be concerned.”
That’s not to say that money should be the only objective though. Palmer comments:
“When I started Oculus, it was not because I thought it would be the thing that made the most money. There had never been a successful VR company in history, to be clear. I did it because it was something I was really passionate about. That said, one of the things that I’m most proud of in my whole career is that everyone who worked at Oculus achieved financial independence because we were able to build something incredible. I feel great that everyone who was part of that mission and supported me early on was able to make a bunch of money, and a lot of them have gone on to do incredible things.”
Video source: @myfirstmilpod (2022)
tweet
Palmer Luckey: If your boss says they don’t care about money, you should be worried
Shaan Puri, host of the My First Million podcast, jokes that “the Silicon Valley thing is to pretend you don’t like money.”
Anduril and Oculus founder Palmer Luckey comments:
“I actually tell our employees during onboarding that if you work at a place where your boss is saying that [money is not the real objective], you should be worried. It’s one thing to say that to the press or your marketing materials, but if your employees don’t believe that at the end of the day you’re trying to make their job a fiscally responsible decision — if you’re effectively telling them that they could be making more money elsewhere and your financial success is not my priority — you should be concerned.”
That’s not to say that money should be the only objective though. Palmer comments:
“When I started Oculus, it was not because I thought it would be the thing that made the most money. There had never been a successful VR company in history, to be clear. I did it because it was something I was really passionate about. That said, one of the things that I’m most proud of in my whole career is that everyone who worked at Oculus achieved financial independence because we were able to build something incredible. I feel great that everyone who was part of that mission and supported me early on was able to make a bunch of money, and a lot of them have gone on to do incredible things.”
Video source: @myfirstmilpod (2022)
tweet
Offshore
Photo
Benjamin Hernandez😎
Banco De Sabadell Appoints TSB’s Marc Armengol as Next CEO https://t.co/RRttygBQcM
tweet
Banco De Sabadell Appoints TSB’s Marc Armengol as Next CEO https://t.co/RRttygBQcM
tweet
Offshore
Photo
DAIR.AI
RT @omarsar0: NEW research on improving memory for AI Agents.
(bookmark it)
As context windows scale to millions of tokens, the bottleneck shifts from raw capacity to cognitive control. Knowing what you know, knowing what's missing, and knowing when to stop matters more than processing every token.
Longer context windows don't guarantee better reasoning. This is largely because the way devs handle ultra-long documents today remains expanding the context window or compressing everything into a single pass.
But when decisive evidence is sparse and scattered across a million tokens, passive memory strategies silently discard the bridging facts needed for multi-hop reasoning.
This new research introduces InfMem, a bounded-memory agent that applies System-2-style cognitive control to long-document question answering through a structured PRETHINK–RETRIEVE–WRITE protocol.
Instead of passively compressing each segment as it streams through, InfMem actively monitors whether its memory is sufficient to answer the question. Is the current evidence enough? What's missing? Where in the document should I look?
PRETHINK acts as a cognitive controller, deciding whether to stop or retrieve more evidence. When evidence gaps exist, it synthesizes a targeted retrieval query and fetches relevant passages from anywhere in the document, including earlier sections it already passed. WRITE then performs joint compression, integrating retrieved evidence with the current segment into a bounded memory under a fixed budget.
The training recipe uses an SFT warmup to teach protocol mechanics through distillation from Qwen3-32B, then reinforcement learning aligns retrieval, writing, and stopping decisions with end-task correctness using outcome-based rewards and early-stop shaping.
On ultra-long QA benchmarks from 32k to 1M tokens, InfMem outperforms MemAgent by +10.17, +11.84, and +8.23 average absolute accuracy points on Qwen3-1.7B, Qwen3-4B, and Qwen2.5-7B, respectively.
A 4B parameter InfMem agent maintains consistent accuracy up to 1M tokens, where standard baselines like YaRN collapse to single-digit performance. Inference latency drops by 3.9x on average (up to 5.1x) via adaptive early stopping.
These gains also transfer to LongBench QA, where InfMem+RL achieves up to +31.38 absolute improvement on individual tasks over the YaRN baseline.
Paper: https://t.co/4wxeCua7a7
Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX
tweet
RT @omarsar0: NEW research on improving memory for AI Agents.
(bookmark it)
As context windows scale to millions of tokens, the bottleneck shifts from raw capacity to cognitive control. Knowing what you know, knowing what's missing, and knowing when to stop matters more than processing every token.
Longer context windows don't guarantee better reasoning. This is largely because the way devs handle ultra-long documents today remains expanding the context window or compressing everything into a single pass.
But when decisive evidence is sparse and scattered across a million tokens, passive memory strategies silently discard the bridging facts needed for multi-hop reasoning.
This new research introduces InfMem, a bounded-memory agent that applies System-2-style cognitive control to long-document question answering through a structured PRETHINK–RETRIEVE–WRITE protocol.
Instead of passively compressing each segment as it streams through, InfMem actively monitors whether its memory is sufficient to answer the question. Is the current evidence enough? What's missing? Where in the document should I look?
PRETHINK acts as a cognitive controller, deciding whether to stop or retrieve more evidence. When evidence gaps exist, it synthesizes a targeted retrieval query and fetches relevant passages from anywhere in the document, including earlier sections it already passed. WRITE then performs joint compression, integrating retrieved evidence with the current segment into a bounded memory under a fixed budget.
The training recipe uses an SFT warmup to teach protocol mechanics through distillation from Qwen3-32B, then reinforcement learning aligns retrieval, writing, and stopping decisions with end-task correctness using outcome-based rewards and early-stop shaping.
On ultra-long QA benchmarks from 32k to 1M tokens, InfMem outperforms MemAgent by +10.17, +11.84, and +8.23 average absolute accuracy points on Qwen3-1.7B, Qwen3-4B, and Qwen2.5-7B, respectively.
A 4B parameter InfMem agent maintains consistent accuracy up to 1M tokens, where standard baselines like YaRN collapse to single-digit performance. Inference latency drops by 3.9x on average (up to 5.1x) via adaptive early stopping.
These gains also transfer to LongBench QA, where InfMem+RL achieves up to +31.38 absolute improvement on individual tasks over the YaRN baseline.
Paper: https://t.co/4wxeCua7a7
Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX
tweet
Offshore
Photo
Bourbon Capital
$AMZN Operating cash flow vs Free cash flow https://t.co/9KdPK1iGk2
tweet
$AMZN Operating cash flow vs Free cash flow https://t.co/9KdPK1iGk2
$AMZN Total debt vs Operating cash flow https://t.co/TKPOFvFic4 tweet
Javier Blas
RT @BarakRavid: U.S.-Iran talks in Oman have ended for today. Another round of talks to take place in the coming days, per source with knowledge
tweet
RT @BarakRavid: U.S.-Iran talks in Oman have ended for today. Another round of talks to take place in the coming days, per source with knowledge
tweet
Offshore
Photo
Wasteland Capital
Absurd guide down at health insurer $MOH, seems borderline criminal. Last Q they guided for ~$14 in ‘26, now they say $3.20 ($5 adjusted)!
I told you last summer to stay the f**k away from health insurers. Know what you own & don’t own sectors under attack.
Stock down -30%. https://t.co/uafPZcQf4o
tweet
Absurd guide down at health insurer $MOH, seems borderline criminal. Last Q they guided for ~$14 in ‘26, now they say $3.20 ($5 adjusted)!
I told you last summer to stay the f**k away from health insurers. Know what you own & don’t own sectors under attack.
Stock down -30%. https://t.co/uafPZcQf4o
tweet
Offshore
Video
Moon Dev
Don't Buy a Mac Mini for Clawdbot: The Secret $10,000 Architecture That Costs You Nothing
clawdbot might be the reason you feel like you need a ten thousand dollar computer right now but i am about to show you why that fomo is going to leave you broke. if you have been watching everyone rush out to buy mac minis and mac studios just to run open claw or some local models you are witnessing a massive transfer of wealth from your pocket to apple for no reason.
there is a specific setup i use that costs almost nothing and keeps my main machine safe from whatever these autonomous agents are doing. if you stick with me i will walk you through the exact architecture of a professional trading system that handles the heavy lifting without you needing to drop a single rack on hardware
most people are scared of running these bots on their main computer because they don't want an agent messing with their personal files or browser sessions. instead of buying a second mac mini for six hundred dollars you can just go to the top left of your screen and create a brand new user profile.
this acts like a completely isolated sandbox where you can install all your trading tools and agents without them ever seeing your main data. it is essentially like getting a free computer for the price of five minutes of clicking around your settings
but what if you aren't on a mac or you need to access your system while you are traveling without carrying three laptops in your backpack. this is where the first loop of professional automation starts to close because i use something called chrome remote desktop to bridge the gap.
this allows me to leave a dedicated machine running in a safe place while i access the full desktop environment from a tablet or a cheap laptop anywhere in the world. it solves the mobility issue but it still doesn't solve the problem of those massive ten thousand dollar price tags for high end mac pros
if you are a pc user or just someone who doesn't want to own physical hardware yet you should look into a windows vps through a provider like contabo. most developers will tell you to use a linux terminal but if you aren't a coder yet you need a visual interface you can actually see.
getting a windows server allows you to log in and see a desktop just like your home computer for about fifteen dollars a month. i usually recommend at least twelve gigabytes of ram to keep things from getting janky when you are running multiple browser windows and agents at once
now you might be thinking that the whole point of the big hardware was to run local models like kimi or glm to save on api costs. i spent years thinking i had to own the machines myself and i even spent hundreds of thousands on developers before i realized i could just do this myself.
the secret to running those massive open source models without the ten thousand dollar investment is renting gpu power by the hour. sites like lambda labs let you spin up a monster machine that can run any model in existence for just a couple dollars an hour
this is the ultimate pivot because it allows you to test if your strategy actually prints money before you commit to the hardware. you can turn the server on when you are iterating and turn it off the second you are done which keeps your overhead near zero.
if you haven't proven that your bot can pay for itself yet then buying a mac studio is just an expensive hobby rather than a business move. there is a much bigger loophole involving the anthropic subscriptions that most people are completely overlooking right now
right now i am using a specific plan with claude code that costs about two hundred dollars a month but it lets me run open claw all day without hitting api limits. if i were paying for those same tokens through the standard api i would probably be spending hundreds of dollars every single day.
it is a massive cost savings that allows you to iterate and fail until you find a winning strategy without draining your bank account. eve[...]
Don't Buy a Mac Mini for Clawdbot: The Secret $10,000 Architecture That Costs You Nothing
clawdbot might be the reason you feel like you need a ten thousand dollar computer right now but i am about to show you why that fomo is going to leave you broke. if you have been watching everyone rush out to buy mac minis and mac studios just to run open claw or some local models you are witnessing a massive transfer of wealth from your pocket to apple for no reason.
there is a specific setup i use that costs almost nothing and keeps my main machine safe from whatever these autonomous agents are doing. if you stick with me i will walk you through the exact architecture of a professional trading system that handles the heavy lifting without you needing to drop a single rack on hardware
most people are scared of running these bots on their main computer because they don't want an agent messing with their personal files or browser sessions. instead of buying a second mac mini for six hundred dollars you can just go to the top left of your screen and create a brand new user profile.
this acts like a completely isolated sandbox where you can install all your trading tools and agents without them ever seeing your main data. it is essentially like getting a free computer for the price of five minutes of clicking around your settings
but what if you aren't on a mac or you need to access your system while you are traveling without carrying three laptops in your backpack. this is where the first loop of professional automation starts to close because i use something called chrome remote desktop to bridge the gap.
this allows me to leave a dedicated machine running in a safe place while i access the full desktop environment from a tablet or a cheap laptop anywhere in the world. it solves the mobility issue but it still doesn't solve the problem of those massive ten thousand dollar price tags for high end mac pros
if you are a pc user or just someone who doesn't want to own physical hardware yet you should look into a windows vps through a provider like contabo. most developers will tell you to use a linux terminal but if you aren't a coder yet you need a visual interface you can actually see.
getting a windows server allows you to log in and see a desktop just like your home computer for about fifteen dollars a month. i usually recommend at least twelve gigabytes of ram to keep things from getting janky when you are running multiple browser windows and agents at once
now you might be thinking that the whole point of the big hardware was to run local models like kimi or glm to save on api costs. i spent years thinking i had to own the machines myself and i even spent hundreds of thousands on developers before i realized i could just do this myself.
the secret to running those massive open source models without the ten thousand dollar investment is renting gpu power by the hour. sites like lambda labs let you spin up a monster machine that can run any model in existence for just a couple dollars an hour
this is the ultimate pivot because it allows you to test if your strategy actually prints money before you commit to the hardware. you can turn the server on when you are iterating and turn it off the second you are done which keeps your overhead near zero.
if you haven't proven that your bot can pay for itself yet then buying a mac studio is just an expensive hobby rather than a business move. there is a much bigger loophole involving the anthropic subscriptions that most people are completely overlooking right now
right now i am using a specific plan with claude code that costs about two hundred dollars a month but it lets me run open claw all day without hitting api limits. if i were paying for those same tokens through the standard api i would probably be spending hundreds of dollars every single day.
it is a massive cost savings that allows you to iterate and fail until you find a winning strategy without draining your bank account. eve[...]