Software Eng in Electronic Design Automation: Building SW to make faster HW. Web3 alt @dfern_eth B4: @Stanford EE, @ECEIllinois https://xitter.cf/t.co/2r7Su0zcEJ
San José, CA
Joined July 2009
- Tweets3.6K
- Following4.3K
- Followers625
- Likes44.8K
Pinned Tweet
I am now on Farcaster permanently
warpcast.com/dfern.eth
and trying out Bluesky
bsky.app/profile/danielferna…
So, Meta's Muse can't use Tailscale, but Grok Bot can? Seems like a big oversight @alexandr_wang
ALT A screenshot that says: Bad news on the Tailscale plan: it's a no-go from this VM, and it's environmental, not a config mistake. My VM's internet goes through a filtering egress proxy — no direct connection at all. Tailscale installed fine, but its login handshake gets a 400 back through the proxy, and even past that, WireGuard's UDP traffic can't traverse an HTTP proxy. So there's no path for my node to join your tailnet or route through dfern-r7 from here. Your idea was sound — a residential exit node is exactly the right fix for the CAPTCHA problem. It's just that this particular VM is network-jailed in a way that blocks it. The fallback stands: I'll route around bot walls with alternate sources where I can, and hand you the browser for the 10-second checkbox when I can't.
Daniel Fernandes retweeted
I coined the term "galactic algorithm" but this week has convinced me it needs to be "multiversal algorithm" 🙃
The "bitter lesson" à la Rich Sutton is that gradient descent blew away 90s era AI: gold standard handcrafted "expert systems." But high throughput screening is already the standard tool in drug target discovery, so IDGI...how is this a "bitter lesson for bio"?
We built an 8000 sqft. high-throughput wet-lab in 30 days, to solve molecular discovery - starting with pesticides.
Most teams in drug-discovery don’t receive target-organism verification until clinical trials. Pesticides allow us to rapidly validate our model in the target organism directly. With the help of our high-throughput lab, we were able to generate compounds that killed a $13 billion pest, the Fall Armyworm.
We believe that the bitter lesson is coming for biology.
We can't. The n log(n)^(1-k) integer multiplication algo is a galatic algorithm. The constants used are so big you could write one bit on every hydrogen atom in the universe and it wouldn't fit. We don't live in a universe where sub n log(n) integer multiplication is possible.
oh yeah btw guys we can do integer multiplication faster than n log n lol
I was definitely very surprised when this one came in lol
github.com/openai/math/tree/…
Daniel Fernandes retweeted
a stranger at dolores park just told me he likes sf better than nyc because new york is a monoculture
it made me realise the sf monoculture people complain about is mostly self-selected. the city has plenty of people who aren't in tech, you just have to step outside the circles you default to
and if you want to stay around tech people but don't want every conversation to be about tech, that's just a skill issue. be more interesting and you'll attract more interesting people
San Jose should be #1, obviously
Daniel Fernandes retweeted
After my PhD, I switched to cancer research because of stories like this. I wanted to use science to make a difference in people’s lives. Reading Susie’s story brings me back to that decision and the hope behind it.
When someone shares something so personal and painful, we owe them more than sympathy. We owe them honesty about what we know, what we don’t, and what our scientific research can realistically accomplish.
Patients’ experiences should never become fundraising appeals that serve institutions more than the people whose suffering gives those appeals their urgency. Their stories should push us to ask harder questions about where the money goes and whether the work deserves the promises made on its behalf.
That includes pursuing basic science whose benefits we cannot yet predict. We need room to discover things we don’t understand. But we should make that case honestly, rather than promise patients or the government that every project is bringing us to a cure.
Stories like Susie’s still inspire me to believe that science can make a difference. They also remind me that our responsibility is to earn that hope through the work we do.
I don’t often write about myself, but today I shared something deeply personal: my experience fighting cancer while continuing to do a job I love.
Cancer tried to make my world smaller. I was determined not to let it.
I am incredibly grateful to be cancer-free, and even more grateful for President Trump, my family, friends, colleagues, medical team and faith that carried me through the hardest days.
I hope sharing my story might offer some strength to even one person still in the fight.
usatoday.com/story/opinion/v…
Daniel Fernandes retweeted
"Don't think for a second that because you are an 'alarmist' that you are doing a social good." Amen.
Crazy that this policy existed in the first place!
Did you know if you tried to open a Trader Joe's, Grocery Outlet, or soon even a Mollie Stone's in San Francisco - you can't?
That's because SF has a rule that formula retail chain stores that have more than 11 stores (worldwide!) can not open in commercial districts without a conditional use permit.
With grocery stores and pharmacies closing across our city, these permits can delay opening new stores by 6-9 months - delaying much needed affordable food in our neighborhoods.
So today I announced legislation to fix it.
Going forward, any parcel already designated as a formula retail chain can convert to a grocery store or pharmacy without an additional conditional use permit. This will save them months on opening.
For any new grocery store that opens, we will also allow them to include a bank, pharmacy, or restaurant without the need for another conditional use permit. As grocery stores consolidate and get smaller, this will help them occupy larger spaces while also bring more needed services to neighborhoods in need.
And lastly, we will add grocery stores and pharmacies to the city's priority processing list.
Importantly, this legislation isn't going to change the character of your neighborhood. It only regulates parcels that are already designated for formula retail chains. Because amidst an affordability crisis restricting access to food and medicine, we need to make it easier to open needed services. Not bury them in red tape.
Thank you Supervisors Sherrill and Melgar for your early cosponsorship of our legislation. We will introduce it at the Board of Supervisors in the weeks ahead, and expect it to pass before the end of the year.
Daniel Fernandes retweeted
>be me
>discover effective altruism
>apparently normal charity is inefficient
>why donate to random sad thing when spreadsheet can tell you optimal sad thing
>fair enough
>buy mosquito nets
>save lives
>numbers look good
>feel powerful
>couple years later
>someone asks an innocent question
>why only count people alive today
>huh
>future people matter too
>obviously
>my grandchildren shouldn't matter less just because they haven't spawned yet
>reasonable.jpg
>keep following logic
>what about their grandchildren
>also yes
>what about people in 500 years
>sure
>5000 years
>why not
>500 million years
>starting to get weird but morality is morality
>open calculator
>humanity could survive for an astronomically long time
>could colonize galaxy
>could have trillions upon trillions of descendants
>maybe digital people too
>maybe simulated civilizations
>maybe dyson spheres full of happy uploaded minds
>calculator starts smoking
>realize currently living humans are rounding error
>8 billion people suddenly looking extremely beta
>future contains potentially 10^something people
>can't even fit beneficiaries in google sheets
>new moral priority unlocked
>protect the long-term future
>stop thinking in units of "people helped"
>start thinking in "fraction of cosmic endowment preserved"
>malaria?
>terrible
>but only kills existing humans
>AI extinction could delete the entire light cone
>nuclear war could permanently derail civilization
>bad institutions could lock in terrible values for ten million years
>someone invents wrong constitution in 2140
>quadrillions suffer
>better fund governance workshop now
>friend says maybe we should improve hospitals
>explain opportunity cost
>friend says hospitals are full of actual sick people
>explain scope sensitivity
>friend stops inviting me to dinner
>need to decide what to fund
>easy
>expected value
>suppose project has one in a million chance of preventing extinction
>sounds tiny
>but extinction destroys 10^50 future lives
>multiply
>mother of god
>$10 million project has expected value of several galaxies
>charity evaluation complete
>someone asks where the one-in-a-million number came from
>expert judgement
>which expert
>us
>how calibrated
>extremely thoughtfully
>reduce estimate to one in ten million to be conservative
>still beats curing cancer by 38 orders of magnitude
>epistemic robustness achieved
>someone says maybe project doesn't work
>assign 20% chance
>still astronomical
>maybe project makes problem worse
>assign 5% chance
>still astronomical
>why 5
>because 30 felt pessimistic
>publish 46-page report
>contains seventeen sensitivity analyses
>every sensitivity analysis begins after assuming intervention has positive sign
>critic says you're multiplying enormous hypothetical stakes by extremely uncertain probabilities
>yes
>that's literally why it's important
>critic says the uncertainty might be structural rather than numerical
>make probability smaller
>critic says no, I mean maybe your model is wrong
>make probability smaller again
>critic begins rubbing temples
>discover AI safety
>perfect longtermist cause
>AI might kill everyone
>or create utopia
>or seize galaxy
>or tile universe with paperclips
>or create billions of conscious software minds
>finally a problem with numbers big enough for me
>start AI safety nonprofit
>mission: prevent dangerous AI
>hire smartest people available
>smartest people immediately start building better AI to understand dangerous AI
>interesting
>we must understand capabilities to understand safety
>we must scale models to study alignment
>we must race ahead so less responsible actors don't get there first
>we must deploy systems to learn how deployment can go wrong
>we must build the thing quickly because building the thing quickly is dangerous
>outsider asks why the people most worried about AI apocalypse all work at AI companies
>complicated field
>company releases stronger model
>very concerned
>company begins training even stronger model
>extremely concerned
>company raises $14 billion
>concern reaches unprecedented levels
>need to influence government
>future is at stake
>normal democratic process too slow
>politicians don't understand exponential curves
>public doesn't understand x-risk
>experts must guide them
>who counts as expert
>people who understand x-risk
>who understands x-risk
>our friends
>someone objects that this seems politically convenient
>explain we're representing future generations
>future generations unavailable for comment
>develop concept of value lock-in
>terrifying possibility that one ideology controls civilization forever
>therefore extremely important that civilization adopts correct values before lock-in
>whose values
>let's circle back
>begin with impartial morality
>end with small group of people deciding what quadrillions of hypothetical beings would want
>beautiful arc
>meanwhile actual humans keep doing annoying things
>voting wrong
>having parochial attachments
>loving family more than strangers
>caring about local community
>getting upset when told their suffering is cosmically negligible
>evolutionary biases everywhere
>explain that moral intuition cannot be trusted
>except intuition that future digital people count
>and intuition that extinction is uniquely bad
>and intuition that our probability estimates are sane
>and intuition that our institutional choices improve the future
>those intuitions survived peer review
>someone donates $5k to local homeless shelter
>inefficient
>could have funded 0.0000000000003% of an AI governance researcher
>think of all the simulated people you just killed
>okay maybe don't phrase it that way publicly
>PR team says "future generations deserve a voice"
>much better
>journalist asks what longtermism means
>say "future people matter"
>everyone agrees
>great
>journalist asks what follows from that
>well technically we should redirect enormous resources toward low-probability interventions affecting astronomical futures
>journalist raises eyebrow
>return to "future people matter"
>motte has entered the chat
>critic: of course future people matter
>me: glad we agree
>critic: I don't agree that your institute knows how to help them
>me: why do you hate our grandchildren
>eventually notice uncomfortable implication
>if future value dominates everything
>then helping people today mostly matters through effects on future
>education matters because future institutions
>health matters because future productivity
>democracy matters because future trajectory
>human beings slowly become instrumental variables in their own moral philosophy
>see starving child
>feel compassion
>check spreadsheet
>child's direct welfare contribution negligible
>but perhaps childhood nutrition improves national institutional quality
>compassion restored
>tell myself this is impartial altruism
>one day assistant asks obvious question
>"how do you know your intervention actually improves the far future?"
>silence
>open spreadsheet
>increase column width
>add confidence interval
>assistant asks again
>"no, I mean how do you know the sign is positive?"
>stare into cosmic light cone
>10^50 people staring back
>none of them exist
>none of them can tell me
>none of them can falsify my assumptions
>realize I have invented the perfect constituency
>infinitely important
>completely silent
>and always represented by me
Daniel Fernandes retweeted
It is hard to convince a man the world is not ending when his self-importance depends upon the idea that it is
This could be a wake up call to accelerate open source AI in biotech: Biology, more than almost any other field, needs fewer gatekeepers.
Furthermore, filling out a form & putting a target on yourself so they can post-train on your prompts is obviously a terrible idea. – at Sunol-Midtown, CA
Today we’re opening applications for the Life Sciences Verification Program.
Through the LSVP, life science professionals can use our models—including, for the first time, Mythos—with a new set of safeguards designed to enable the full range of biology-related work. We designed these new safeguards to provide a better experience for biologists and more protection from risk of misuse.
The program is launching in beta for teams of all kinds—from academic labs to startups, pharma companies, and more. We will continue to improve the program and expand access to individual Pro and Max plans over time.
Learn more about these access grants and apply: anthropic.com/news/life-scie…
Daniel Fernandes retweeted
I’ve expected this for a while but it still hurts. The “Life Sciences Verification Program.” It breaks my heart to know that biological knowledge will be locked down and gatekept like this. I want to take a moment to mourn, because I believe this marks an end for open science as I knew it.
I think back to my education. I owe so much to the open-access literature. I'm so deeply thankful to the culture of transparency among scientists. All the free knowledge I've been given. The free GenBank sequences. The free PDB structures. The education and know-show that my colleagues shared with me for the pure love of learning.
The Life Sciences Verification Program will kill that spirit. The most important biology tools of the next decade will be locked down and controlled. Some fragments of the old literature will remain free, but the real heart of where science happens will not be free. Frontier knowledge will belong only to people who the authorities decide deserve it.
I want to fight this, but I don’t think I can. I don’t believe bioterrorism is a serious threat, but convincing people of that is not realistic. The fear is embedded too deep in the psyche. If I tried, there are armies of internet trolls eager to accuse me of evil things. It would become my entire online life.
There is a growing and well funded fear-industrial complex dedicated to the idea that Bio-AI is a terrible risk and the people who practice it need to be monitored and policed. Hundreds of full-time professionals whose salary depends on their belief that biology presents a dire threat. What hope do I have of arguing with them?
On the other side, the traditional defenders of free information are historically weak. Biology professors are struggling just to keep the lights on. The last thing they want is to be called reckless enemies of national security. They aren’t going to fight this - I’m sure many of them are already signing up to ask for permission to be on the list.
So I’m writing this to bear witness. This is how it ended. Biology isn’t going to be free going forward. That was an idea of the pre-AI era and it is over now. The fight now isn’t over free access to information. It’s over who gets verified access to the closed information.
Big pharma companies get permission, of course. So do professors at elite universities. But we can petition Anthropic to expand that list. Maybe they might allow access for high school teachers, medical students and nurses? I hope they will approve farmers, iGEM teams, community biolabs, birdwatchers, park rangers and community gardens.
Will Anthropic allow those people to study biology at the frontier? As of today, the power officially belongs to them. We can only ask.
Today we’re opening applications for the Life Sciences Verification Program.
Through the LSVP, life science professionals can use our models—including, for the first time, Mythos—with a new set of safeguards designed to enable the full range of biology-related work. We designed these new safeguards to provide a better experience for biologists and more protection from risk of misuse.
The program is launching in beta for teams of all kinds—from academic labs to startups, pharma companies, and more. We will continue to improve the program and expand access to individual Pro and Max plans over time.
Learn more about these access grants and apply: anthropic.com/news/life-scie…
Daniel Fernandes retweeted
Guy who makes a living from YouTube is against datacenters now
What are we even doing here man
