Naka-pin na Tweet
SPAR
57 posts
SPAR
@SPARexec
We're a part-time, virtual research program that gives students and early career professionals an opportunity to work with professional AI safety researchers.
Sumali Mart 2024
79 Sinusundan525 Mga Tagasunod
SPAR nag-retweet
Applications for the Generator Residency close on Monday EOD! Last chance to apply.
Fully funded, 6k stipend + travel + housing, 3 months with an extension, in-person in Berkeley. Probably the best path into AI safety for non-researcher roles.
Agus 🔸@austinc3301
Announcing the Generator Residency: a 3-month residency for AI safety generalists, by @KairosAIS × @ConstellOrg. Fully funded. In-person in Berkeley. Summer 2026. 🗓 Apply by April 27 generatorresidency.org/?utm_source=tw…
English
SPAR nag-retweet
📣 Only 3 days left to apply for Generator!
Apply by April 27, to join our inaugural cohort with advisers from AI Futures Project, BlueDot, Coefficient Giving, FAR. AI, Forethought, METR, RAND, and more!
generatorresidency.org
English
SPAR nag-retweet
Announcing the Generator Residency: a 3-month residency for AI safety generalists, by @KairosAIS × @ConstellOrg.
Fully funded. In-person in Berkeley. Summer 2026.
🗓 Apply by April 27
generatorresidency.org/?utm_source=tw…
English
SPAR nag-retweet
Excited to share our new paper! We looked at when reasoning LLMs 'knew' their final answer internally vs. when it was stated in chain-of-thought. Turns out these models can be performative depending on the task!
Goodfire@GoodfireAI
LLMs often reason “performatively” well after deciding on a final answer - something that CoT monitors are slow to catch. Our new paper finds that: - probes can help monitor for this - it seems to track with task difficulty - probes enable early CoT exit, saving tokens! (1/7)
English
life update: spending this summer in berkeley doing tensor network research at @BerkeleyLab! looking forward to living in the area for the first time.
also recently got accepted as a @SPARexec fellow and will be working on mechanistic interpretability!
English
SPAR nag-retweet
In this work, we complement behavioral goal-directedness evals of LLM agents with a probing analysis of environment and plan representations, examining whether observed actions are consistent with models' internal beliefs, and how reasoning affects representations. Check it out!
Mario Giulianelli@glnmario
When we say an AI agent is “goal-directed”, what do we actually mean? In new work from Project Telos, we study this question by combining behavioural evaluation with analysis of internal representations in a language model agent navigating grid worlds. 1/
English
SPAR nag-retweet
SPAR nag-retweet
LawZero is accepting applications as part of the SPAR Spring 2026 program!
If you're interested in studying model awareness or emergent misalignment, you can learn more and apply here: sparai.org/projects/sp26/.
Applications are open until Jan 14, 2026.
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
SPAR nag-retweet
Come work with me and @SPARexec to build an AI mech interp researcher to accelerate AI safety research.🧠🔬
In the last cohort, my mentees built AI agents that automatically find and refine explanations for SAE features (demo of what they built after only one month below). In this cohort, we want to push for agents that discover and explain full circuits.
Deadline is Jan 14th!⏳🗓️
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
Apply here before 11:59 PM AoE on Wednesday, January 14th!
sparai.org/projects/?utm_…
English
SPAR nag-retweet
I'm mentoring a SPAR project on evaluating and refining alignment targets for LLMs (constitutions, model specs, etc.) this spring! Apply by January 14 to work with me or other SPAR mentors - project details/application link ⬇️:
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
SPAR nag-retweet
SPAR nag-retweet
The NYU Center for Mind, Ethics, and Policy is seeking research fellows to contribute to upcoming reports on legal personhood and economic rights for digital minds. Please apply if you have interest in working with us!
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
SPAR nag-retweet
Join me next Spring in exploring how time is represented in LLMs 🕓
Deadline: January 14th
sparai.org/projects/sp26/…
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
SPAR nag-retweet
I'm a SPAR mentor, if you'd like to work on solving Anthropic cyber espionage type attacks, please do apply!
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
SPAR nag-retweet
I'm glad to mentor again for this round of SPAR, likely with @zhonghaohe! Together let's help human-AI coevolution go a little bit better :)
⬇️🧵Here's a collection of research ideas I'd be excited to mentor projects on. Feel free to pitch yours too!
SPAR@SPARexec
🚀 We're excited to announce that mentee applications are now open for the Spring round of the SPAR research program! This will be our largest round ever, featuring 130+ projects across AI safety, policy, governance, security, welfare, and strategy.
English
We've also added biosecurity projects this round!
Explore the available projects and mentors here:
sparai.org/projects/?utm_…
English