Quite a claim in this new work from Goodfire. Among many points, they argue that some of the main examples of superposition and polysemanticity in large models were misunderstood. This definitely deserves some deep, rigorous peer review. already-clean.goodfire.com
Shahab Bakhtiari
Researcher with public evidence across AI research.
- AI signals
- 2 past 30d
- Sources
- 1 distinct domains
- Discussions
- 6 past 30d
- Latest signal
- 17d ago
Articles & links
I think the evidence is growing and gaps are closing; this is from a few years ago: proceedings.neurips.cc/paper_files/..., and things've been improving since then. Of course, there are skeptics ...
I’m thinking even beyond image labeling—more in the realm of recent self-supervised learning methods (e.g., what we proposed here: proceedings.neurips.cc/paper_files/...). There’s really cool work bringing these concepts into visual neuroscience (we and others have been doing …
Nice analysis of citation patterns between neuroscience and AI: www.thetransmitter.org/computationa... There are some interesting signs of growing citations of neuroscience studies in AI post-2020. The part I found most interesting is that most citations are from pre-2000, lan…
- Renato Duarte's citation analysis of about 458 million OpenAlex publications finds the neuroscience-AI connection 'real and gaining momentum' but 'narrow, tool-heavy and concentrated.'
- The most recent paper bridging both fields dates to 2003, and roughly half the strongest cross-field citations are statistical or ML tools like XGBoost and lme4.
- The top 100 institutions produce nearly 40% of bridging work, led by Alphabet and Microsoft, ahead of MIT, UC Berkeley, Harvard and Stanford.
Acemoglu et al.’s case for "pro-worker AI" makes so much sense. The common counter to #AI job loss is that tech always creates new work. Acemoglu argues that new jobs don't appear spontaneously, especially if we don't actively build AI to complement workers. www.brookings.edu/…
In a similar vein, I previously wrote about why reconstructing animals’ ecological experiences matters; and how AI can help: www.thetransmitter.org/artificial-i...
Recent commentary
I’ve been thinking… now that AI is taking on groundbreaking, award-winning problems across science, what are those equivalent problems in #neuroscience? What would one of these models actually have to do to leave us all in awe? 🧠🤖
Astra’s most striking leap across several fronts (eg robotic control) boils down to spatial intelligence. I used to think genuine spatial understanding was impossible for language models without physical real-world interaction. Well … Astra proved that wrong or it's far more than just a mere LLM
In Shahab Bakhtiari's orbit
Center = Shahab Bakhtiari. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Shahab Bakhtiari? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/shahabbakht-bsky-social)