Eylon Bachar

197 posts

Eylon Bachar banner
Eylon Bachar

Eylon Bachar

@eylon1234

People, freedom and hard problems. Happy dad.

Israel Katılım Mart 2012
449 Takip Edilen68 Takipçiler
hiteyjit
hiteyjit@hiteyjit·
every humanoid demo i've seen is, in my opinon, bottlenecked by the same thing: we have great actuators and no ground truth for intent. as a start, upstream EMG is probably the cheapest true intent sensor that already exists beyond CV. i'm surprised people haven't wired it to more stuff i'd do it
English
1
1
2
36
khalil
khalil@khal_ism·
the sublime begins to reveal itself. 07.15.26
English
9
2
28
6.2K
Dr. Uke
Dr. Uke@DrUkeAging·
🧬 Thoughts from the scientists who shaped aging research: “We should not expect there to be a single mechanism of aging.” — Tom Kirkwood This is one of the most important lessons from evolutionary theories of aging. Aging is not simply telomeres, DNA damage, mitochondria, senescence, inflammation, or proteostasis collapse alone. These mechanisms interact, reinforce each other, and vary across tissues, species, and individuals. Kirkwood’s disposable soma theory helped frame aging as a problem of imperfect maintenance: evolution did not necessarily optimize the body for indefinite repair. That is why aging biology is so complex and so fascinating. 🔬
English
2
3
10
1.2K
Sagar
Sagar@Sagar_kr_Maity·
"If I had an hour to solve a problem I'd spend 55 minutes thinking about the problem and 5 minutes thinking about solutions." — Albert Einstein
Sagar tweet media
English
1
5
25
954
Eylon Bachar
Eylon Bachar@eylon1234·
@aquinasheard23 Likewise. I think they’re starting to. “Unschooling” is getting popular in the US, and hopefully it will propagate fast.
English
0
0
1
47
aquinas heard
aquinas heard@aquinasheard23·
Just maybe….as many parents are fretting about social media for kids/teens (sometimes understandably)…..they will eventually turn this scrutiny to what’s “under the hood” in their local public school….a guy can dream
English
2
1
5
289
Jérémie
Jérémie@jeremiegags·
hardware vs software is so H1 2026, time for a new category semiware
English
2
0
3
211
Dr Singularity
Dr Singularity@Dr_Singularity·
Cure diseases. Automate labor. Expand intelligence. Multiply energy. Explore the universe.
English
26
52
570
112.6K
Eylon Bachar
Eylon Bachar@eylon1234·
@ivnbkrv No. But I'll gladly offload all non-creative thinking.
English
0
0
0
12
Ivan Bokarev (in sf)
Ivan Bokarev (in sf)@ivnbkrv·
would you be happy to offload structured conscious reasoning to AI, and become an intuitive-only species?
English
1
0
0
152
Eylon Bachar
Eylon Bachar@eylon1234·
@SterlingCooley Per OrchOR theory we need a quantum computer to model mt dynamics. Regardless, I think a nested neural network architecture will be beneficial nonetheless. @StuartHameroff
English
0
0
1
36
Sterling Cooley
Sterling Cooley@SterlingCooley·
Okay business idea here guys: Why don't we try building silicon chips just like the 6 cortical layers of the brain ? And model Microtubule dynamics the most in layer 5, just the way nature did it to give us consciousness ?
Sterling Cooley tweet media
Sterling Cooley@SterlingCooley

Pyramidal Neurons, which are super-rich in Microtubule pairings (dense) are likely the true "embedding" location of a 6 layer cortical stack. Eventually mainstream neuroscience will catch up We are so early guys :D haha

English
5
0
31
2.4K
hiteyjit
hiteyjit@hiteyjit·
hey, i'm hiteyjit. i'm a neuroscientist, founder, filmmaker, builder of cool hardware, and ever so occasional philosopher. been building machines since i was 8 – first for myself, then a nonprofit i founded at 12 that scaled across three countries teaching kids to make their own. somewhere in there i noticed the machine i cared most about was the one actually doing all the building; so, i pivoted into neuroscience @ uoft and then spent a year at harvard stimulating the hell out of some neurones. the one ground truth i've found though all this i've found is that people only believe what they can physically feel; every other medium is borrowing trust from that one. if it were up to me, id change the laws of physics so its easier for me to decode inner thoughts. since i can't, i'm doing the next best thing by building beautiful instruments for the mind with some phenomenal people. sf is now home #7. reach out if you're here + you make physical things (films count) + you're up for having your worldview argued with!
hiteyjit tweet mediahiteyjit tweet media
English
4
2
12
910
Eylon Bachar retweetledi
Conjecture Institute
Conjecture Institute@ConjectureInst·
Poverty is caused by nothing—it is the state of Nature into which humanity was born. Meanwhile, wealth is not some mana from the sky delivered by fiat or by Nature but rather must be created by man. Like knowledge in contrast with ignorance, it is wealth, not poverty, that demands explanation. ~Conjecture Institute President @ChipkinLogan
Institute of Economic Affairs@iealondon

💰 "Wealth taxes, that's the thing about them. They have been tried many, many times before. This is not a remotely new idea." @K_Niemietz on @PiersUncensored tells @garyseconomics that half of Western Europe had wealth taxes until the early 1990s, and abolished them for good reason.

English
2
7
31
1.8K
Eylon Bachar retweetledi
David Deutsch
David Deutsch@DavidDeutschOxf·
@visegrad24 The enemies of civilisation typically attack too early.
English
24
37
432
31.4K
Eylon Bachar retweetledi
Isaak
Isaak@isaakfreeman·
How did we achieve so fast end-to-end testing? Our proprietary Capable Core: We verticalized key steps of preclinical development. Our platform consists of 6 semi-autonomous modules, most of which we re-engineered to run 10–20x faster. Drug design, ML infra, rapid synthesis, quality control, cell testing, and then mouse testing. Our first modality at the 24h pace is binders & peptides--including complex modifications, cyclization, and noncanonical amino acids. Mouse studies: For many of the biologically fast readouts, such as our short sleeper programs, we are able dose new drugs in placebo-controlled in vivo studies within that 24h period too and can read out early significant differences between drug candidates rapidly. We achieved this through an in vivo facility in the lab, pre-approved protocols, and veterinarians & in vivo researchers on standby. This doesn't work for all indications: For Alzheimer's models the time-to-first-signal in vivo read-out is longer. For all drug candidates, before clinical testing we do standard chronic studies.
English
3
4
106
15.3K