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[...]
Offshore
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…
n if they eventually close this loophole or snitch on the usage patterns it serves as the perfect training ground for a data dog
the goal is to find a system that works with a smaller or cheaper model like haiku before you ever try to scale up to the heavy weights. if you can make a strategy profitable using a less intelligent and cheaper model then you know you have found real alpha.
once you have that foundation you can decide if it finally makes sense to build your own custom pc rig which will always be half the price of an apple machine. i am an apple guy so i usually pay the tax anyway but i only do it once the system is already generating enough to cover the cost ten times over
i believe that code is the great equalizer because it took me from losing money and getting liquidated to having fully automated systems doing the work for me. i had to learn to live with the iterations and the failures on youtube to get to this point of clarity.
the universe tends to get out of your way once you make a non negotiable contract with yourself to see the process through to the end. you don't need the flashy hardware or the most expensive setup to start winning in this game
stay focused on the logic and the data rather than the hype and the fomo that everyone else is falling for. if you can master the bridge between renting power and owning your logic you will be ahead of ninety nine percent of the people in this space.
the path to a fully automated life isn't paved with expensive gadgets but with the discipline to iterate until the system finally prints
tweet
the goal is to find a system that works with a smaller or cheaper model like haiku before you ever try to scale up to the heavy weights. if you can make a strategy profitable using a less intelligent and cheaper model then you know you have found real alpha.
once you have that foundation you can decide if it finally makes sense to build your own custom pc rig which will always be half the price of an apple machine. i am an apple guy so i usually pay the tax anyway but i only do it once the system is already generating enough to cover the cost ten times over
i believe that code is the great equalizer because it took me from losing money and getting liquidated to having fully automated systems doing the work for me. i had to learn to live with the iterations and the failures on youtube to get to this point of clarity.
the universe tends to get out of your way once you make a non negotiable contract with yourself to see the process through to the end. you don't need the flashy hardware or the most expensive setup to start winning in this game
stay focused on the logic and the data rather than the hype and the fomo that everyone else is falling for. if you can master the bridge between renting power and owning your logic you will be ahead of ninety nine percent of the people in this space.
the path to a fully automated life isn't paved with expensive gadgets but with the discipline to iterate until the system finally prints
tweet
Offshore
Video
Lumida Wealth Management
Elon Musk just said space will be the cheapest place to run AI in 36 months
There's a physics problem with running AI on Earth that nobody's talking about.
Earth's atmosphere kills 30% of solar energy before it reaches your panels. Add in day-night cycles and massive battery costs, and you're fighting a losing battle.
Space has none of that.
Same solar panel generates five times more power. No batteries needed.
Musk's prediction is under 36 months before space becomes the cheapest option for AI infrastructure.
While Big Tech burns billions on Nevada data centers, the real advantage might be 200 miles up.
Companies building ground-based AI today could pay five times more than competitors in three years. That's extinction-level disadvantage.
SpaceX proved everyone wrong about reusable rockets. Starlink made satellite internet work.
Now, @elonmusk says the AI race won't be won in Silicon Valley.
Three years. Maybe less.
Here are some key takeaways from @elonmusk recent interview with @dwarkesh_sp and @stripe
tweet
Elon Musk just said space will be the cheapest place to run AI in 36 months
There's a physics problem with running AI on Earth that nobody's talking about.
Earth's atmosphere kills 30% of solar energy before it reaches your panels. Add in day-night cycles and massive battery costs, and you're fighting a losing battle.
Space has none of that.
Same solar panel generates five times more power. No batteries needed.
Musk's prediction is under 36 months before space becomes the cheapest option for AI infrastructure.
While Big Tech burns billions on Nevada data centers, the real advantage might be 200 miles up.
Companies building ground-based AI today could pay five times more than competitors in three years. That's extinction-level disadvantage.
SpaceX proved everyone wrong about reusable rockets. Starlink made satellite internet work.
Now, @elonmusk says the AI race won't be won in Silicon Valley.
Three years. Maybe less.
Here are some key takeaways from @elonmusk recent interview with @dwarkesh_sp and @stripe
tweet
Offshore
Photo
Benjamin Hernandez😎
This isn't for the public. We’ve found an under-the-radar play institutions are hiding while they accumulate. I’m only sharing this with the inner circle.
Join the circle: 👉 https://t.co/71FIJId47G
Reply “SILENT” for the confidential ticker.
$BMNR $BYND $NB $ASST $PULM
tweet
This isn't for the public. We’ve found an under-the-radar play institutions are hiding while they accumulate. I’m only sharing this with the inner circle.
Join the circle: 👉 https://t.co/71FIJId47G
Reply “SILENT” for the confidential ticker.
$BMNR $BYND $NB $ASST $PULM
📊 Professional Pick: $CISS
Entry: $2.28 | Target: $3.42
Technicals are flawless. $CISS just broke out of a multi-week base on record volume. RSI is rising but not yet overbought.
One-line why: The 50% gain today is just the "ignition phase." The target is the $3.42 resistance https://t.co/XkSQnEtkah tweet