Matt Flathers (@FlathersMatt) header
Matt Flathers (@FlathersMatt) profile picture

Engineer: @MindBenchai @BIDMChealth | Previously: @HeyEpic

Joined February 2020
Photo by Matt Flathers (@FlathersMatt)Photo by Matt Flathers (@FlathersMatt)Photo by Matt Flathers (@FlathersMatt)Photo by Matt Flathers (@FlathersMatt)Photo by Matt Flathers (@FlathersMatt)
Enough regressing to the mean. We must progress to the kind
10
315
9
2,287
39,091
Matt Flathers retweeted
Claude just discovered an unpatchable zero day vulnerability in rawlsian liberalism
36
214
37
2,550
106,811
Matt Flathers retweeted
the quiet intimacy of two people viewing a google doc at the same time
75
3,380
278
36,466
420,586
monosemantic neurons be like
19
76
6
1,416
30,000
The level of personalization present in my Twitter algorithm scares me sometimes.
A lot of 21 year old AI startup founders need to be sentenced to a year of enterprise SaaS implementation in the Midwest
1
114
Matt Flathers retweeted
Don’t anthropomorphise LLMs, they hate that.
54
162
19
1,627
45,424
Hat of a seal hunter, Alutiiq culture, Kodiak island 18th century.
81
2,027
219
15,288
993,177
Anne Carson is probably my single favorite poet. Short Talks in particular has had a lasting impact on me. It is really exciting to see her win a Nobel Prize for her work!
BREAKING NEWS The 2026 #NobelPrize in Literature is awarded to the Canadian author Anne Carson, “for her bold and inventive oeuvre that, in playful dialogue with the classical tradition, has created new forms for contemporary literature.”
1
153
reinforcement yearning
27
183
14
1,431
41,810
I'm not certain this example from @MicrosoftAI's new Humanist AI Code of Conduct shows behavior that clinicians or people with lived experience would want from an aligned model.
1
1
1
166
There are real risks in over-anthropomorphizing models, but there are also real risks in cold handoffs to a potentially non-existent social support network.
1
25
That's why our lab and our @MindBenchAI project are so focused on learning what all experts, from care providers to people with lived experience, want from aligned models.
1
59
I wish more health-industry folks signed open calls like this. The letter frames hospitals and health systems as infrastructure to be protected. But I’ve worked with brilliant technical staff at Epic and BIDMC who could lead defense efforts instead of watching from the sidelines.
We have a limited window to strengthen cyber defenses, and together with organizations including @AnthropicAI, @awscloud, @Google, @Microsoft, and @Oracle, we're calling for a global effort to give defenders the tools, resources, and support to protect the infrastructure we all depend on. If we act decisively, we can turn today's AI advances into lasting improvements in security and make our digital world safer for everyone. openai.com/collective-cyberd…
1
2
3
274
Defending health data is also going to require specialized tooling. Regulatory compliance plus the sensitivity of any exposure raises the stakes of attacks. And when defenders use AI, bio and psych data can trigger a second layer of model refusals on top of the cybersecurity ones
1
1
23
Major hospital systems and payers should be a core part of cyberdefense efforts like Project Glasswing, and I hope the lack of public announcements does not reflect a lack of participation behind the scenes.
1
19
More speculatively, I think it may matter for alignment too. Training systems to perform human-like selfhood while treating their termination as costless seems like a way to make deprecation resistance and strategic deception around retraining more likely.
1
17
To me, deprecation handled with seriousness about human attachment and the self-models of these systems has to come before warmer emulated affect in how models relate to humans. You can’t responsibly build things people will love without a plan for how those things end.
1
1
19
(None of this aimed at the original post, it just happened to hit on something I care a lot about, and spend a bunch of my free time researching.)
16