Milan Weibel 🔷
@weibac.bsky.social
clarity is a public good
weibac.github.io | 🏳️🌈 | 22
weibac.github.io | 🏳️🌈 | 22
Pinned
Milan Weibel 🔷
@weibac.bsky.social
· May 4
updating your beliefs is not painful
it is resisting the update that is painful
by letting go of wrong beliefs you embrace reality
such is the bayesian dharma
it is resisting the update that is painful
by letting go of wrong beliefs you embrace reality
such is the bayesian dharma
once the quantitative benchmarks saturate we will be left with stuff like this
As a fan of weird but revealing benchmarks, I enjoyed this historian’s attempts to have different frontier AIs build “a full featured RPG game where you play as Henry James wandering as a flâneur at the 1889 Universal Exposition in Paris.” HenryBench? open.substack.com/pub/resobscu...
How well can Gemini 3 make a Henry James simulator?
Finally, a benchmark for LLMs with real-world value
open.substack.com
November 19, 2025 at 1:32 PM
once the quantitative benchmarks saturate we will be left with stuff like this
im sorry but too many huggingface models are shrimp brains overfit to codeforces problems
November 18, 2025 at 10:19 PM
im sorry but too many huggingface models are shrimp brains overfit to codeforces problems
oh you're a metal fan?
you must be old since all the new ones are plastic
you must be old since all the new ones are plastic
November 18, 2025 at 10:16 PM
oh you're a metal fan?
you must be old since all the new ones are plastic
you must be old since all the new ones are plastic
heck yea
November 18, 2025 at 4:09 PM
heck yea
maybe one day we will be strong enough to liberate our brains from our bodies
but i think we will probably never liberate our minds from our brains
but i think we will probably never liberate our minds from our brains
the great self-liberation of humanity is precisely our self-liberation from the shackles of our natural condition--yes, including our natural biology. fuck that noise
November 18, 2025 at 12:51 AM
maybe one day we will be strong enough to liberate our brains from our bodies
but i think we will probably never liberate our minds from our brains
but i think we will probably never liberate our minds from our brains
@segyges.bsky.social the authors of AI 2027 pushed back their timelines
> the authors of AI 2027 think that their “strong AGI in 2027” scenario is plausible, but faster than their median expectations. The median timelines of Daniel, Eli, and Thomas for when we will develop strong AGI are 2030, 2035, and 2033, respectively.
Good collaborative piece between the authors of AI 2027 and those of AI as Normal Technology on areas of shared agreement
t.co/h82vvrYRPM
t.co/h82vvrYRPM
November 16, 2025 at 2:42 PM
@segyges.bsky.social the authors of AI 2027 pushed back their timelines
> the authors of AI 2027 think that their “strong AGI in 2027” scenario is plausible, but faster than their median expectations. The median timelines of Daniel, Eli, and Thomas for when we will develop strong AGI are 2030, 2035, and 2033, respectively.
Good collaborative piece between the authors of AI 2027 and those of AI as Normal Technology on areas of shared agreement
t.co/h82vvrYRPM
t.co/h82vvrYRPM
https://asteriskmag.substack.com/p/common-ground-between-ai-2027-and
t.co
November 16, 2025 at 2:30 PM
> the authors of AI 2027 think that their “strong AGI in 2027” scenario is plausible, but faster than their median expectations. The median timelines of Daniel, Eli, and Thomas for when we will develop strong AGI are 2030, 2035, and 2033, respectively.
CHILEAN ELECTIONS THREAD
November 15, 2025 at 10:41 PM
CHILEAN ELECTIONS THREAD
debating whether to Post A Lot about tomorrow's elections
candidates for next chilean presidential election sorted by rough polling average (polls noisy):
- tankie aunt who denies that cuba and venezuela are dictatorships but is otherwise mostly chill
- chilean bolsonaro
- chilean margaret thatcher
- sexist milei cosplayer
- extremely divorced grifter
...
- tankie aunt who denies that cuba and venezuela are dictatorships but is otherwise mostly chill
- chilean bolsonaro
- chilean margaret thatcher
- sexist milei cosplayer
- extremely divorced grifter
...
November 15, 2025 at 9:44 PM
debating whether to Post A Lot about tomorrow's elections
Reposted by Milan Weibel 🔷
🔥 WANTED: Student Researcher to join me, @vdebortoli.bsky.social, Jiaxin Shi, Kevin Li and @arthurgretton.bsky.social in DeepMind London.
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
Student Researcher, 2026 — Google Careers
google.com
November 15, 2025 at 5:23 PM
🔥 WANTED: Student Researcher to join me, @vdebortoli.bsky.social, Jiaxin Shi, Kevin Li and @arthurgretton.bsky.social in DeepMind London.
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...
chilean news is taking this very seriously
breaking news on prime time, long analysis treatment
breaking news on prime time, long analysis treatment
November 14, 2025 at 12:15 AM
chilean news is taking this very seriously
breaking news on prime time, long analysis treatment
breaking news on prime time, long analysis treatment
reading baguettotron thinking traces reminds me of the uplifted lobsters from the novel accelerando: they're alien and still confused about human language but clearly there's some thinking going on
Breaking: we release a fully synthetic generalist dataset for pretraining, SYNTH and two new SOTA reasoning models exclusively trained on it. Despite having seen only 200 billion tokens, Baguettotron is currently best-in-class in its size range. pleias.fr/blog/blogsyn...
November 13, 2025 at 9:31 PM
reading baguettotron thinking traces reminds me of the uplifted lobsters from the novel accelerando: they're alien and still confused about human language but clearly there's some thinking going on
i love how he's implying that journalists are not folks
For folks (and journalists) who want to search the Oversight Committee email texts, I made a database for searching the 20k text files:
splendorous-chaja-f79791.netlify.app
splendorous-chaja-f79791.netlify.app
Epstein Document Search
splendorous-chaja-f79791.netlify.app
November 13, 2025 at 4:18 PM
i love how he's implying that journalists are not folks
"you can install uv to the conda environment through pip"
vLLM docs who hurt you
vLLM docs who hurt you
November 13, 2025 at 12:50 PM
"you can install uv to the conda environment through pip"
vLLM docs who hurt you
vLLM docs who hurt you
henry george vs houses georg
houses georg
November 11, 2025 at 7:11 PM
henry george vs houses georg
thread on corporate incentives + LLM alignment techniques leading to LLM delusion-facilitation
Commercial AI has a serious problem in that they try to design it for being a "a safe, pleasant, and endlessly available conversational partner" and thats one of the flaws that makes it hallucinate more. Its hedging and unwillingness to upset anyone is causing it to lie.
November 11, 2025 at 12:29 PM
thread on corporate incentives + LLM alignment techniques leading to LLM delusion-facilitation
good comic to surface into discourse but even really precise specs are different from code
10 years old and maybe never more relevant than in contemporary software development
www.commitstrip.com/en/2016/08/2...
www.commitstrip.com/en/2016/08/2...
November 11, 2025 at 11:32 AM
good comic to surface into discourse but even really precise specs are different from code
extreme training efficiency from fully synthetic pretraining
Breaking: we release a fully synthetic generalist dataset for pretraining, SYNTH and two new SOTA reasoning models exclusively trained on it. Despite having seen only 200 billion tokens, Baguettotron is currently best-in-class in its size range. pleias.fr/blog/blogsyn...
November 10, 2025 at 8:20 PM
extreme training efficiency from fully synthetic pretraining
i love the fact that llama.cpp is distributed via brew nix winget compiling from source and nothing else
like they know their linux users are too cool to download a .deb and yet they also want to offer a windows option
like they know their linux users are too cool to download a .deb and yet they also want to offer a windows option
November 10, 2025 at 12:21 AM
i love the fact that llama.cpp is distributed via brew nix winget compiling from source and nothing else
like they know their linux users are too cool to download a .deb and yet they also want to offer a windows option
like they know their linux users are too cool to download a .deb and yet they also want to offer a windows option
slightly old article but openai is still working on the prevention of LLM psychosis
says they're tweaking gpt5 but i think the most at-risk users are those still choosing to use gpt4o
says they're tweaking gpt5 but i think the most at-risk users are those still choosing to use gpt4o
OpenAI released initial estimates about the share of users who may be experiencing symptoms like delusional thinking, mania, or suicidal ideation, and says it has tweaked GPT-5 to respond more effectively.
OpenAI Says Hundreds of Thousands of ChatGPT Users May Show Signs of Manic or Psychotic Crisis Every Week
OpenAI says hundreds of thousands of ChatGPT users may show signs of manic or psychotic crisis every week.
wrd.cm
November 8, 2025 at 9:53 PM
slightly old article but openai is still working on the prevention of LLM psychosis
says they're tweaking gpt5 but i think the most at-risk users are those still choosing to use gpt4o
says they're tweaking gpt5 but i think the most at-risk users are those still choosing to use gpt4o
new kind of chart crime dropped
G1, prominent Brazilian news outlet, posted an approval rating graph which has an inverted Y axis.
Despite Governor Cláudio Castro's approval rating increasing 10% (from 43% to 53%), the approval line appears decreasing.
Despite Governor Cláudio Castro's approval rating increasing 10% (from 43% to 53%), the approval line appears decreasing.
November 8, 2025 at 1:12 PM
new kind of chart crime dropped
Reposted by Milan Weibel 🔷
🎉 ICML 2026 Call for Papers (& Position Papers) is here! 🎉
📅 Key Dates
Abstract deadline: Jan 23, 2026 AOE
Paper deadline: Jan 28, 2026 AOE
A few key changes this year:
- Attendance for authors of accepted papers is optional
- Originally submitted version of accepted papers will be made public
...
📅 Key Dates
Abstract deadline: Jan 23, 2026 AOE
Paper deadline: Jan 28, 2026 AOE
A few key changes this year:
- Attendance for authors of accepted papers is optional
- Originally submitted version of accepted papers will be made public
...
November 7, 2025 at 2:42 PM
🎉 ICML 2026 Call for Papers (& Position Papers) is here! 🎉
📅 Key Dates
Abstract deadline: Jan 23, 2026 AOE
Paper deadline: Jan 28, 2026 AOE
A few key changes this year:
- Attendance for authors of accepted papers is optional
- Originally submitted version of accepted papers will be made public
...
📅 Key Dates
Abstract deadline: Jan 23, 2026 AOE
Paper deadline: Jan 28, 2026 AOE
A few key changes this year:
- Attendance for authors of accepted papers is optional
- Originally submitted version of accepted papers will be made public
...
having a subordinate that's way smarter than you is a very weird relationship dynamic
November 6, 2025 at 9:10 PM
having a subordinate that's way smarter than you is a very weird relationship dynamic
is there a unicode proposal for the seahorse emoji yet
November 6, 2025 at 1:50 PM
is there a unicode proposal for the seahorse emoji yet