Russ Fischer
superelastic.bsky.social
Russ Fischer
@superelastic.bsky.social
even AI could not do that
November 17, 2025 at 7:21 PM
🎶
I am Dr Worm
I'm interested in things
I'm not a real doctor
But I am a real worm
I am an actual worm
I live like a worm
November 17, 2025 at 4:39 PM
I'm a three line whip I'm the sort of thing they ban
I'm a walking disaster, I'm a demolition man
November 15, 2025 at 6:12 PM
The ICE rejection is not limited to VA either. Pennsylvania: Voters Ousted This Pennsylvania Sheriff After He Signed Up to Collaborate With ICE | Bolts share.google/leSmp6NTQdaT...
Voters Ousted This Pennsylvania Sheriff After He Signed Up to Collaborate With ICE - Bolts
A populous, swing county replaced its GOP sheriff on Tuesday after months of controversy over his joining ICE’s 287(g) program. The Democratic winner promises he’ll end the contract.
share.google
November 13, 2025 at 1:19 PM
bailed after three seconds
youtu.be/jL2DcWB994s?...
Jeremy Renner - "Main Attraction"
YouTube video by Jeremy Renner
youtu.be
November 7, 2025 at 7:27 PM
Fantastic. What is the mechanism that retracts the string so smoothly?
November 6, 2025 at 12:52 PM
you are living the rock and roll life I can only dream of
November 6, 2025 at 11:56 AM
a bit off topic, but I think you might be interested: [2509.06917] Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents share.google/EXK2F7c7EZda...
Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents
We introduce Paper2Agent, an automated framework that converts research papers into AI agents. Paper2Agent transforms research output from passive artifacts into active systems that can accelerate dow...
share.google
November 2, 2025 at 12:00 PM
probably this one: arxiv.org/html/2406.14...

people are working on fixes (LLM combined with symbolic knowledge representation): arxiv.org/html/2411.12...
Insights into LLM Long-Context Failures: When Transformers Know but Don’t Tell
arxiv.org
October 30, 2025 at 4:14 PM
It's a known prob with AI tutors using general-purpose LLMs - performance degrades because the attention mechanism can't consistently use context across the long chat.

U could try Google's Notebook LM - you feed it the docs you want it to work with and it favors info found in the docs you fed it.
October 30, 2025 at 11:35 AM
ok so not 'creator'. how bout 'unearthing what everyone else missed'
October 27, 2025 at 9:08 PM
man, he knows how to tee it up for Gavin Newsom's team
October 27, 2025 at 5:07 PM
I saw this, and now I have a bottle of azelastine nasal spray ready to go next time I'm locked in a conference room. This is just my person paranoia, though not medical advice.
jamanetwork.com/journals/jam...
Azelastine Nasal Spray for Prevention of SARS-CoV-2 Infections
This randomized clinical trial evaluates the efficacy of azelastine as a preexposure prophylaxis against SARS-CoV-2 and other respiratory pathogens.
jamanetwork.com
October 27, 2025 at 5:03 PM
I'm using these AI models all day long (for software development) but like you fascinated by the bigger picture. I know Deep Mind and others are working on "world models" so the LLM test hypotheses in the "world"

From www.nytimes.com/2023/03/08/o...
October 27, 2025 at 3:28 PM
I have the same crisis when I see "half roasted chicken" on the menu
October 26, 2025 at 2:28 PM
That's why I've been tormenting Pulte Homes lately.
October 24, 2025 at 1:59 PM
thanks for the reminder 👍
October 23, 2025 at 11:46 AM
the boys should go make their own.
it sure won't look like that though
October 21, 2025 at 3:12 PM
that was a glorious rant, bravo
October 20, 2025 at 4:05 PM