Nissa Seru

Karma: 3,192

Nissa Seru 19 Jun 2026 20:18 UTC
2 points
0
on: World-modeling the US vs. Anthropic Standoff on Claude Fable
without opining directly on the methodology or predictions (i lack a sufficiently-strong domain model), i would observe that your beliefs suggest that you can mill your prediction-harness for money by pointing it at prediction markets. would bet you can find many bets that resolve quite quickly to get a quite good rate of return.

so tenatively, i would screen off the specifics here, and simply ask you in a week or so how much money you have made i think?

Nissa Seru 16 Jun 2026 21:31 UTC
2 points
0
in reply to: TurnTrout’s comment on: TurnTrout’s shortform feed
I was unable to find from a quick check in the repo—is jailer used to run firecracker? If not, might be worth highlighting and speaking to the tradeoffs; IIUC amazon does not recommend using firecracker as a security boundary without jailer (outside of my expertise, but my understanding is that this is because firecracker-alone means escape is just a single KVM-escape away, which are not unheard of) - if such a non-standard config is being used, it may be worth highlighting so that folks don’t mistakenly assume that firecracker is being used in the config recommended by its authors.

for clarity, this is not intended as a veiled “y u no use jailer this sucks”—i do not in fact have any particular opinion on such, but i do think it is really easy for folks to misunderstand the level of security that a given setup provides, such that specifics on that front might be particular helpful to convey

Nissa Seru 15 Jun 2026 3:09 UTC
2 points
0
in reply to: Hastings’s comment on: TurnTrout’s shortform feed
not an alignment researcher, but i do run all agents in a firecracker vm (within jailer) unless they need host access (in which case i give them that, and watch closely.) security is part of this, but also the isolation helps parallel agents not be confused since they don’t risk stumbling into other agents worktrees.

Nissa Seru 14 Jun 2026 0:05 UTC
9 points
1
in reply to: TurnTrout’s comment on: TurnTrout’s shortform feed
thanks for making this. just as note, if you haven’t already done so, highly recommend asking claude and gpt to pentest from inside, maybe with a concrete flag like creating evil.txt in your homedir on host.

Nissa Seru 11 Feb 2022 14:20 UTC
3 points
0
on: The Long Long Covid Post
Thank you for this post! One feedback—I found this post much harder to navigate than your other posts (and eventually resorted to summary+bookmark); it is much easier for me to parse/navigate when post sections follow your own line of thinking than when they are structured as replies to sections of other peoples’ posts.

Nissa Seru 30 Dec 2021 22:54 UTC
4 points
0
in reply to: wunan’s comment on: Covid 12/30: Infinity War
i have worn this on an airplane with a surgical mask over the exhale valve
https://www.amazon.com/GVS-SPR457-Elipse-Respirator-Medium/dp/B013SIIBFQ/ref=sxts_rp_s1_0?cv_ct_cx=gvs+elipse+p100&gclid=CjwKCAiAzrWOBhBjEiwAq85QZyLzBYwxwOZcFGAMZbn4S6OVwxcQXnl1L6L9xWu1dQgzAFdKK8oxOhoCqo0QAvD_BwE&hvadid=409918312011&hvdev=c&hvlocphy=9014238&hvnetw=g&hvqmt=e&hvrand=6118992613772945421&hvtargid=kwd-267611734495&hydadcr=20509_11115072&keywords=gvs+elipse+p100&pd_rd_i=B013SIIBFQ&pd_rd_r=03b1c070-7191-4557-b0bb-79b3930e0ac8&pd_rd_w=JYxDi&pd_rd_wg=uF7dV&pf_rd_p=53ef7f8b-c1cb-4ebe-8d67-39f3ca0ebaf7&pf_rd_r=PE758N16XDW0FMZ1MZXD&psc=1&qid=1640904683&sr=1-1-5e1b2986-06e6-4004-a85e-73bfa3ee44fe

Nissa Seru 19 Aug 2021 17:13 UTC
2 points
0
on: Bupropion and CBD oil
Without knowledge of potential interactions, melatonin might be another option—I don’t take bupropion, but suspect that one would take daily dose in morning to minimize chance of this side effect as well

Nissa Seru 24 Jul 2021 7:39 UTC
9 points
0
on: ($1000 bounty) How effective are marginal vaccine doses against the covid delta variant?
Depending on when you got your second mRNA dose, the Israeli data suggests there is significant vaccine decline in vaccine efficacy after 3 months (see https://www.gov.il/BlobFolder/reports/vaccine-efficacy-safety-follow-up-committee/he/files_publications_corona_two-dose-vaccination-data.pdf ) This does not of course indicate whether a third dose would restore efficacy (presumably by reigniting the immune response in some way) - I suspect it would, however. No need for prize money if relevant—just resharing a link that was already in Forbes https://www.forbes.com/sites/roberthart/2021/07/23/pfizer-shot-just-39-effective-against-delta-infection-but-largely-prevents-severe-illness-israel-study-suggests/?sh=ca1146c584f1

Nissa Seru 15 Jul 2021 19:51 UTC
8 points
0
on: Covid 7/15: Rates of Change
Thanks for this as always! Any thoughts on the variant effectiveness estimates in this paper?

https://www.medrxiv.org/content/10.1101/2021.05.22.21257658v1.full-text

Nissa Seru 17 May 2021 16:17 UTC
4 points
0
in reply to: someonewrongonthenet’s comment on: Covid 5/13: Moving On
The initial pfizer efficacy study and followups in Israel specifically come to mind.

Nissa Seru 9 May 2021 20:46 UTC
19 points
0
on: MIRI location optimization (and related topics) discussion
Potential metrics which may be helpful to consider (from a previous location search for me to live): Minimum sunlight per month, months under 200 hrs of sunlight, days above 90F, days below 32F, snow/rain days per year, violent crime level, property crime level, number of internet providers, average speed test result of internet providers, top advertised speed of internet providers, quality of healthcare, attends religious services at least once per week, rate of cigarette use, rate of alcohol use, rate of binge drinking.
Some of these are direct metrics on experience (ie number of days where climate makes being outside less pleasant), others towards the end of the list are more proxy metrics of concrete data that may give some indication of general level of religiosity/stress/need for escape in the local environment.

Nissa Seru 30 Apr 2021 0:26 UTC
2 points
0
in reply to: digital_carver’s comment on: Better air is the easiest way not to die
Great, thank you

Nissa Seru 29 Apr 2021 8:09 UTC
6 points
0
on: Better air is the easiest way not to die
Would love any context here—not sure if I should parse the linkpost as random person on internet saying things or if any background that would give me a higher prior that their models are accurate and/or useful.

Nissa Seru 18 Apr 2021 17:59 UTC
4 points
0
in reply to: JesperO’s comment on: The Case for Extreme Vaccine Effectiveness
Fluvoxamine is a prescription drug in the FDA, so your doctor can prescribe it; https://www.pushhealth.com/ might work as well. Antiviral procurement is similar if the antiviral you’re seeking is a US prescription drug (in any case I’d consider Googling the antiviral name.)

Nissa Seru 14 Apr 2021 2:37 UTC
8 points
0
on: The Case for Extreme Vaccine Effectiveness
Apologies in advance for not engaging in detail with the analysis itself—my overall synthesis here is that residual risk does exist post-vaccination and is potentially non-negligible. Personally I’ll be using my Oura ring to detect nighttime temperature spikes and use a high-accuracy at-home test (https://checkit.lucirahealth.com//) if I detect a spike, followed by aggressive treatment with fluvoxamine (+potential antiviral) if the test comes back positive—these safeguards feel sufficient to travel (airplane) to see family, etc without incurring significant risk of long-term health impacts. Appreciate the work to get a tighter bead on the risk itself (and depending on conclusions, some of the above may not have great marginal risk reduction), but wanted to share as one possible mitigation strategy that I expect to be robust even in pessimistic risk-branches.

Nissa Seru 27 Feb 2021 18:49 UTC
2 points
0
on: Why aren’t we all using Taffix?
I’m curious if anyone knows of research comparing effectiveness of this to povidone iodine nasal spray? I make a 0.8% solution of that and use it in nose and gargle before going out (in addition to mask)

Nissa Seru 27 Feb 2021 9:59 UTC
2 points
0
in reply to: pjeby’s comment on: Why aren’t we all using Taffix?
ebay

Nissa Seru 10 Feb 2021 22:57 UTC
2 points
0
in reply to: Nissa Seru’s comment on: Still Not in Charge
Thank you both! Zvi—makes sense re short duration of increased interest and effective to capitalize on it while that lasts. Rob—the part I’m not seeing is the causal link between these posts and influencing/improving decisions made by the FDA and CDC.

Nissa Seru 9 Feb 2021 22:20 UTC
2 points
0
on: Still Not in Charge
Out of curiosity, how come the strong speed premium on these posts? AFAICT there’s nothing here that informs short-term decisions for readers; I’ve been skimming and mostly tossing into my to-read pile for that reason. Know I’m not exactly an important stakeholder here, but personally I’d sorta prefer to read the synthesis from a chat between yourself and Scott rather than the blow-by-blow.

Nissa Seru 25 Jan 2021 9:01 UTC
5 points
0
on: You can send people KN95s
You can even send them actual N95s https://www.lesswrong.com/posts/kdkFnRnZv4ut5qGhR/?commentId=RaLK7uGHynTdny6Zf#RaLK7uGHynTdny6Zf