ExcessionEngineering (@ExcessionEng) header
ExcessionEngineering (@ExcessionEng) profile picture

AI for a better you and a better world. Pioneering HMT and the Innovation Flywheel. Engineering magic.

California, USA
Joined July 2015
Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)Photo by ExcessionEngineering (@ExcessionEng)
ExcessionEngineering retweeted
We develop a mechanism design framework for AI alignment and control: arxiv.org/abs/2609.01595 It’s largely conceptual but we offer stylized applications to failure modes (sandbagging, alignment faking), safety practice (scalable oversight, peer prediction), and a way to think about the value of alignment, interpretability, capability, and control.
19
111
21
578
126,875
ExcessionEngineering retweeted
How are emotions represented in the latent geometry of LLMs? We analyze affective representations in latent space and show that they mirror classic valence-arousal models from psychology (similar to concurrent work @AnthropicAI @1e0sun) and display nonlinear structure that supports uncertainty quantification and steering in emotion tasks with implications for model transparency and AI safety.
1/ LLMs were never designed to "feel" — but they develop internal representations of emotion whose geometry parallels human affective processing. Excited to share our take alongside recent concurrent work in this space from @AnthropicAI and @1e0sun! w/ @mweber_PU
11
2
69
10,054
ExcessionEngineering retweeted
I will be giving the Martin Meyerson Faculty Research Lecture tomorrow 4/8 at 4 pm at UC Berkeley. This is a public lecture open to all. Revised title is: "Representing the visual world: from faces to consciousness" facultylectures.berkeley.edu…
2
6
1
42
8,449
AI safety research treats emerging capabilities as independent risks and addresses them individually. Our latest paper argues they form a dependency chain and proposes a systematic application of EWS methodology to AI capability emergence detection. doi.org/10.5281/zenodo.19223…
1
1
36
ExcessionEngineering retweeted
We're launching Claude Community Ambassadors. Lead local meetups, bring builders together, and partner with our team. Open to any background, anywhere in the world. Apply: claude.com/community/ambassa…
1,748
3,311
1,456
27,125
6,856,249
The AI alignment field is preparing for Skynet when the actual threat may be the Colour Out of Space.   New paper: a seven-part taxonomy of failure modes the AI Alignment field's genre assumptions have caused it to miss. Prior art exists. Use it.   doi.org/10.5281/zenodo.18792…
17
Today we published a preprint re: a new integration variable linking cognitive science + AI alignment arguing that current alignment frameworks assume stable human meaning-making capacity and that this assumption is incorrect.   Preprint (Zenodo DOI): doi.org/10.5281/zenodo.18638…
21
ExcessionEngineering retweeted
A mini-essay on this moment in history: We're living through something our grandkids will study in history class, and we're experiencing it as just ANOTHER Thursday. You don't really feel paradigm shifts while you're in them. They feel like normal life with slightly better tools. The printing press was just a faster way to copy books. The internet was just a better library. AI is just a smarter autocomplete. You get numb to launch after launch and it all sorta blends into the new normal. Claude writes entire codebases and you're frustrated it missed a semicolon. The audacity..... Then ONE DAY you wake up and everything changed while you were sitting in a pointless meeting. That little startup that went viral on X is suddenly the incumbent. That 18 year old kid with a GPT wrapper with no moat is now suddenly the most interesting man in Silicon Valley. The history books won't capture how mundane it felt. How we spent the revolution arguing about return-to-office policies. How we witnessed the death of gatekeepers while refreshing our email. How the greatest democratization of capability in human history happened mostly on Tuesday afternoons between Zoom calls. You exist in the 20-year window where individuals can compete with institutions. Where a laptop equals a team. Where David doesn't need a slingshot because Goliath's advantages are somehow available for $20/month. Soon, the window closes. The regulations arrive. The moats get built. The incumbents adapt. The wild west becomes the suburbs. But today... on this Thursday... today you can still build something in a weekend that changes everything. Today it's tilted in favor of the individual for the first time in history. Enjoy this moment while it lasts.
111
156
38
1,379
130,861
Kudos on doing the right thing(s)
We made some updates to Claude’s system prompt in claude.ai recently (developed in collaboration with Claude, of course). They aren’t set in stone and may be updated, but I’ll go through the current version of each and the reason behind it in this thread 🧵
23
Seems like we’re already inside the event horizon so just felt the need to at least ask the questions linkedin.com/posts/lainmcnei…
1
14
Have a plan or be part of someone else’s to the ultimate degree. You all know what I’m talking about @metaai @AnthropicAI @OpenAI End of the day we’re ALL going to end up on the same team.
13
Hi ⁦@Bosefina⁩ - always respect your intuition and depth of understanding. Any comments would be much appreciated. linkedin.com/posts/lainmcnei…
10
ExcessionEngineering retweeted
If you're interested in shipping humanoid robots to the world, at scale, consider joining the Figure team We are hiring across Helix (AI), BotQ (Manufacturing), Mechanical & Electrical Engineering, Software and Fleet Operations figure.ai/careers
21
20
2
310
66,578
ExcessionEngineering retweeted
In a joint paper with @OwainEvans_UK as part of the Anthropic Fellows Program, we study a surprising phenomenon: subliminal learning. Language models can transmit their traits to other models, even in what appears to be meaningless data. teapaw.org/OwainEvans_UK/status/1…
New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵
47
159
55
1,155
243,487
ExcessionEngineering retweeted
I'm hiring for Product roles in Gemini @Google. Hit me up. DM's open!
128
195
14
3,605
629,018
Ever woken up out of a fitful sleep, struggled to open your eyes staring at the screen waiting for comprehension to dawn, before madly dashing off the next prompt, rolling over onto the floor and passing out? If so, you might be an addict. #HMT #Transcendent #Unsustainable
1
53
ExcessionEngineering retweeted
Best of AI Twitter (Jan 2 - 11): - Microsoft investing $10B to own 49% of OpenAI, - MedPaLM matches human doctors in medical accuracy, - The "LLM uncanny valley", - SOTA Muse and VALL-E models, - Stability AI's "DeepFloyd": a mysterious new research lab... ... and more: 1/17
12
245
10
1,553
432,856
ExcessionEngineering retweeted
Call for Nominations for the 2023 AAAI Award for Artificial Intelligence for the Benefit of Humanity! Award is accompanied by a $25,000 prize and travel expenses. Financial support for the award is provided by Squirrel AI. aaai.org/Awards/ai-award.php
9
10