Conan (@_Conan0x) header
Conan (@_Conan0x) profile picture

poasting

🌴USA🌴
Joined May 2025
Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)Photo by Conan (@_Conan0x)
Conan retweeted
Update on World 2-1. I froze the 1-1 player built on @rei_labs Adapt-1 and added two small learners, the correctors, that can replace one of its moves. It now clears 2-1 and still clears 1-1.
Can Adapt-1 by @rei_labs learn to play Super Mario Bros without demonstrations? We tried it on World 1-1, starting untrained. It learned a reactive policy from its own play in about 36 minutes of gameplay, then cleared the level with learning off.
1
2
5
287
Conan retweeted
The thread below summarizes the method and its results. The complete version is in the article, and the docs show how to issue, revise and score forecasts through the API. Article: reilabs.org/blog/forecasting… Docs: docs.reilabs.org/docs/neuroa…
1
4
15
618
Conan retweeted
We’re introducing case-based probabilistic forecasting in Adapt-1, learned at test time from a cold start, with no recalibration layer. Each forecast gets a prequential energy score, and the stored scores set the mixture weight between a kernel over similar cases and a prior.
11
37
5
132
5,126
Conan retweeted
The article covers the method in detail: the adaptive state and its routes, how each revision is scored against its parent, the sequence stages, and results across 12 chemostat runs of 4,000 attempts each. Article: reilabs.org/blog/reinforceme… Docs: docs.reilabs.org/docs/neuroa…
1
3
23
893
Conan retweeted
Evolutionary methods in RL often ignore which actions each candidate takes during its episode. Today we explore Reinforcement Learning over Executed Trials: Adapt-1 revises the commands that ran and scores each revision against the run it came from. 🧵
15
35
3
125
4,471
And we're gonna do it all without frontier models under the control of a rent-seeking cartel that sought regulatory oversight for the sole purpose of pricing out competitors with compliance overhead.
Anthropic CEO predicts cancer, Alzheimer's, heart disease, mental illness will be cured in less than 10 years ACCELERATE
14
51
2
803
13,453
Conan retweeted
Latest explorations in reinforcement learning and planning from @rei_labs Learning from crude experience: Learning from scratch without demonstrations, expert move labels or engine evaluations. Points scored against base Stockfish (beginner) rose from ~56% to ~84% under the same planning settings. Retained learning: Applying a previously learned skill to new starting conditions. Machina succeeded on 34/64 starts without further search, or 52/64 with evaluation search.
Introducing CLP: coupled learning and planning from limited experience and delayed outcomes. Learning guides trials; planning and execution generate evidence. We study a response to inevitable training-data scarcity, starting with adversarial decision-making and machine control.
4
11
40
1,133
Conan retweeted
Introducing CLP: coupled learning and planning from limited experience and delayed outcomes. Learning guides trials; planning and execution generate evidence. We study a response to inevitable training-data scarcity, starting with adversarial decision-making and machine control.
22
43
6
216
13,515
Conan retweeted
rei coded
Bear thesis: AI revenues are not increasing fast enough to fulfill CAPEX obligations and growth is slowing ++ opensource margin compression Bull thesis: AI labs will eventually be able to stop pretraining, demand for intelligence is infinite and margins are very high
1
3
15
638
Conan retweeted
1
1
6
394
Conan retweeted
The source code is on GitHub, now with clips of both ways Adapt-1 played: its decision loop and its Machina control sequence. github.com/hsrvc/adapt1-mari…
Can Adapt-1 by @rei_labs learn to play Super Mario Bros without demonstrations? We tried it on World 1-1, starting untrained. It learned a reactive policy from its own play in about 36 minutes of gameplay, then cleared the level with learning off.
2
11
2
88
200,763
Continual Learning visualized:
Can Adapt-1 by @rei_labs learn to play Super Mario Bros without demonstrations? We tried it on World 1-1, starting untrained. It learned a reactive policy from its own play in about 36 minutes of gameplay, then cleared the level with learning off.
4
27
1,171
Ten years ago, AlphaGo’s Move 37 shocked the world. It wasn’t intuition alone that produced it. AlphaGo could search possible futures, test its instincts and reason about what would happen next. In a new piece for @techreview, I argue that today’s most advanced AI systems are still missing something fundamental. LLMs are remarkably capable, but generating longer chains of thought is not the same as genuine reasoning. They typically have no explicit, inspectable record of what they know, what remains uncertain, what evidence supports a conclusion or whether genuine progress has been made. This is why I recently left @GoogleDeepMind. I believe we need a fresh approach to machine reasoning, drawing on some of the architectural lessons from AlphaGo. If AI is going to produce trustworthy and genuinely novel insights in science, medicine and beyond, we need systems whose conclusions arise from an auditable process of evidence, inference and belief revision.
50
114
34
689
99,434
Conan retweeted
Can Adapt-1 by @rei_labs learn to play Super Mario Bros without demonstrations? We tried it on World 1-1, starting untrained. It learned a reactive policy from its own play in about 36 minutes of gameplay, then cleared the level with learning off.
11
29
6
101
371,098
I recommend to Trump that he ignore the aspiring cartel's apocalyptic warnings. He should understand those efforts as attempts to reframe the failure of their models to follow instructions as proof of their value, and to shift attention away from the fact that the models are basically Huffman codec encoded collections of intellectual property. Since they exist by virtue of massive intellectual property infringement, the argument that the models should be anything other than a public good doesn't need to be entertained. It makes more sense for the AI cartel to pivot to an infrastructure monopoly along the lines of traditional telecom, like AT&T. This is where economies of scale actually will obtain, and where a rent-seeking economic model is more tolerable from a public policy standpoint.
A seating chart for a White House "Super Intelligence" luncheon was posted by President Trump. Elon Musk, Mark Zuckerberg, Jensen Huang, Sundar Pichai, Jeff Bezos and Satya Nadella are among the tech leaders listed.
6
38
3
257
15,467
Conan retweeted
Just Plumbing... Already cleared 8-fig trades on 2/3 of these tokens since this post. VVV, I hold my last 10%. That was a monster trade for me because it let me double tap it.....Thanks Dragonfly crew for putting the fear of GOD in people by talking nonsense. NEAR, I had been accumulating since it was below 1. It took its sweet ass time, but as soon as ZEC started to take off, I knew the entire privacy sector was going to reprice, and NEAR was the best bet with the biggest spread against ZEC. Add to that all the new ships and the lack of supply overhang, and I knew it had to be a winner. I still hold 60% of my position and will keep selling every time the chart breaks key resistance. AERO, I still hold 100% of my position. Not a bad trade, but not the best one either. RH motion stole the mojo on this one, I still think it gives me my 2.5x tho.... What trades are next? One that excites me, Variational. I have been farming it non-stop and, as I have been saying, this team is special. It ain't just another perps protocol, they have a very creative and original approach to what they are building, and we already saw a glimpse of it with the swaps market. If you have been following me for a while, you know I put two wallets in the top 30 on HYPE after Jeff rejected my investment check, and I am about to do the same on VAR. VAR can play out two ways.....It can behave similarly to HYPE, where we just go up and up until it reaches the comp valuations everyone is already charting (HYPE, LIT, ASTER), or it can do what I call the LONG U, where everyone sells it into oblivion and, once that process is exhausted, it shoots up (see LIT). If we get the LONG U, you will see me buying a shit ton more on top of my airdrop around the bottom of that U. If we don't, you will see me buy a shit ton on top of my airdrop when they inevitably face their dragon. One that intrigues me, TIBBIR. I was able to accumulate a ton of it around the 110M range. I am intrigued by what Micky Malka will cook with this one.....I respect that dude a ton and like the way he thinks, and that alone was enough for me to size what I thought, and hoped, was the bottom. This is a dangerous trade because expectations among holders are so high that whatever gets revealed might simply fail to meet them. I have been debating cutting a ton here (50% of the position), but I have decided to play ball. If the reveal sucks, I will most likely roundtrip the trade....buuut if it doesn't......I could 5x this with size. One that is nerdy, REI. I have been accumulating a good amount of it below 15M. This one is pure excitement about what this team might achieve by making AI adaptive after deployment instead of largely freezing intelligence at inference. If you are an AI power user, you will probably be as excited as I am. One that is rogue, ASTER. I have been building a size on it....Yep...I just can't fade 280+ days of accumulation and a lovely LONG U chart. As you can see, every trade above has the same underlying structure....Setups where I can reasonably underwrite 20–30% of downside while having a path to 2–3x on the upside. Bear markets make these setups easier to find because prices can compress far more violently than the underlying opportunity, but they exist in every market.....This is my arena. You see.... When I was finally able to play with size, I started thinking differently about how to play the game and eventually found myself applying the logic behind the Kelly Criterion to the way I trade....It's simple, once you have size, maximizing the return on any single trade becomes less important than maximizing the number of times you can bet that capital to favorable asymmetry without meaningfully impairing the base. If you have read all the way to here, stick with me, you will probably get something out of this. It’s weird but many never care to think that wealth does not grow arithmetically, it’s all multiplicatively. If you start with 100, lose 50%, then make 50%, you are not back at 100. You go: 100 → 50 → 75. So even though the average return between those two trades is 0%, your wealth is down 25%. Ouch, right? Geometric compounding problem..... Every return you make is being earned on whatever capital base the previous trade left behind, which means large losses do much more damage than they first appear to....Which matters enormously once you start playing with size because the base itself becomes the most valuable part of your game. When your base is small, you are forced to look for insane multiples because even a great percentage return won't change your life in the ways you dream of....So if you have 20K and want to make 2M, you need a 100x. That necessity naturally pushes you into chasing insane upside....buuuut....most of those trades come with a nasty fkn failure rate attached to them too. When you are finally able to play with size, that necessity is no longer there, and you need to readjust. You need to be a tad more boring because now, with 20M on hand, a 10% return makes you the same 2M, which buys the same things as the 100x 2M. Which changes the hunt completely.....you can stop digging through shit for 1000xs and start hunting fat asymmetry with size. Now, you can spend your time looking for trades where you think you can lose 20–30% if you are wrong and make 2–5x if you are right, and then keep doing that over and over again with meaningful size. When the base gets large enough, every percentage point you earn on it becomes meaningful in absolute terms, and every time you protect it, you preserve the ability to keep compounding from a larger denominator. 10M becomes 20M. Now another 2x is not another 10M, it is 20M. Do it again and it is 40M. Which means you do not need increasingly crazier trades, just favorable setups applied to an increasingly larger base. I’ll tell you this, size does make the game easier, but only if you stop trading like you are still trying to escape the basement.....If you already have size and you are still mentally trapped in the 10,000x cage, eventually you are going to blow yourself tf up. Stop chasing miracles, if you are already trading size there is a very good chance you already had one or two break your way.....take the gift and stop going back to the market begging for another one.
Fuck the turtles... I just pulled out the big straw and will start slurping the coins I like... I have enough solvency to outlast the market’s irrationality. VVV AERO NEAR (for now) All while I farm Variational.
30
21
10
346
42,727
Conan retweeted
Adapt-1 Developer Docs v1.0 is live. We’ve rebuilt the docs around getting started with Adapt-1 and understanding what you can build with it. Quickstarts, API reference, mechanisms, traces, integration guidance, and use cases. docs.reilabs.org/docs/neuroa…
14
39
4
129
7,132
Nobody explains what base:0x6b2504a03ca4d43d0d73776f6ad46dab2f2a4cfd actually is, so here it is: Rei labs is building "Core," a persistent reasoning model, and "Adapt-1," a system that learns online with no pretraining. Instead of generating one answer and stopping, it keeps a live field that updates as it reasons. 🧵
5
21
3
87
9,193