←
Reshmi Ghosh1,862 posts
Reshmi Ghosh avatar

Reshmi Ghosh

@reshmigh

Sr. Scientist working on Agents,Reasoning, AI Security, @Microsoft AI, Chair @WiMLDS| Ph.D. @CarnegieMellon | making machines trustworthy| Views my own; She/Her

◷ Joined July 2013▧ 101 Photos and videos
Srishti avatar
⟳ Reshmi Ghosh retweeted
Srishti@seekingsrishti·Jul 20

I confronted senior Delhi police officers why they used tear gas and lathi charge against the protestors. Listen to their response.

1:21
Hua Shen✨ avatar
⟳ Reshmi Ghosh retweeted
Hua Shen✨@huashen218·5 Nov 2025

🧐Are values in LLMs aligned with humans? 1️⃣ And if they are — do LLMs stay honest to those values, or sometimes say one thing but act another? 2️⃣ ✨ We explore these questions in two papers presented at #EMNLP2025: 1️⃣ ValueCompass: hua-shen.org/assets/files/al… (WiNLP Workshop) 2️⃣ Mind the Value–Action Gap: arxiv.org/pdf/2501.15463 (Main Track) 🔍 Dataset & Code: github.com/huashen218/value_… 🌱 I’m also #Hiring multiple PhD students for Fall 2026 @ NYU Courant Computer Science! If you’re passionate about #Human_AI_Alignment, #Value_Alignment, or broad #AI + #Human (society) research, let’s connect at EMNLP2025, NeurIPS2025, or over Zoom! 🎓 NYU CS PhD Apply (NYU Shanghai Track): cs.nyu.edu/dynamic/phd/admis… 💜 This year I’m also co-organizing the #EMNLP2025 WiNLP Workshop and supporting the amazing #Tutorial on Spoken Conversational Agents with LLMs (a short 15min talk)! Come say hi 👋 — I’d love to chat and connect with old and new friends at #EMNLP2025! 🔗 WiNLP Workshop: winlp-workshop.github.io/ 🔗Tutorial on Spoken Conversational Agents: aclanthology.org/2025.emnlp-… 💗Huge thanks to my wonderful paper collaborators — @tanmit,@YunHuang_HCI,@tknearem,@reshmigh,Nicholas Clark,Yu-Ju Yang — and my inspiring workshop/tutorial collaborators @huckiyang, Andreas Stolcke,@TYSSSantosh2,@therealthapa,@MeryemMhamdi1,Chen Zhang, Peerat Limkonchotiwat, Wiem Ben Rim.... 🤗Truly grateful and enjoyable to work with you all! 💫 #HumanAIAlignment #PhDOpening #NYU #NYUShanghai #ValueAlignment #HAI

Post attachmentPost attachment
Myra avatar
⟳ Reshmi Ghosh retweeted
Myra@myra_deng·29 Oct 2025

Using probes to accurately and efficiently detect model behavior (in this case PII leakage) in prod is one of the clear wins for applied interpretability. This is the path to semantic determinism - imagine AI models instrumented with internal probes that recognize when they’re hallucinating, going off-policy, or posing biorisk, and resteering themselves accordingly.

Goodfire@GoodfireAI29 Oct 2025

Why use LLM-as-a-judge when you can get the same performance for 15–500x cheaper? Our new research with @RakutenGroup on PII detection finds that SAE probes: - transfer from synthetic to real data better than normal probes - match GPT-5 Mini performance at 1/15 the cost (1/6)

Post attachment
Lily Xu avatar
⟳ Reshmi Ghosh retweeted
Lily Xu@lilyxu0·29 Oct 2025

Launching AI for Public Goods Fast Grants! We'll distribute $150k to advance critical work connecting AI and public goods. 💰 $10k per project 💰 $800 reviewer compensation PUBLIC GOODS := open source, ecosystem services, climate, urban infra, comms, education, science, & more

David Dao@dwddao14 Oct 2025

Announcing AI for Public Goods Fast Grants (AI4PG) - Up to $10K for AI research improving public goods funding. Fast review (2-3 weeks), simple applications (4 pages + 1 budget page), open to any researchers worldwide. Call for reviewers now open! recerts.org/ai4pg2025

Post attachment
Niloofar avatar
⟳ Reshmi Ghosh retweeted
Niloofar@niloofar_mire·20 Oct 2025

I'm recruiting students for fall 2026 thru @LTIatCMU & @CMU_EPP, in: 1. Privacy & security of LLMs, coding, long horizon & embodied agents (robotics) 2. Tiny local llms 3. AI for scientific reasoning, esp. chemistry 4. Latent reasoning 5. anything YOU are passionate about!

Reshmi Ghosh avatar
Reshmi Ghosh@reshmigh·8 Oct 2025

It is an infinite glitch circle now!

But who are these reviewers? They are the same authors. I think we should teach young members of our community to value "learning a new nugget of information" over "obtaining a bold number in a table."

Sarah Sachs avatar
⟳ Reshmi Ghosh retweeted
Sarah Sachs@sarahmsachs·6 Oct 2025

Being at top of @OpenAI token usage list is a vanity metric. Our job as engineers is to minimize token usage (aka latency and cost) while maximizing value by precise tool definitions and clever model routing. My dream is to grow arr and move lower on this list…

Post attachment
Reshmi Ghosh avatar
Reshmi Ghosh@reshmigh·1 Oct 2025

Can someone in the room define what is the commonly accepted definition of AGI?

Haider.@haider130 Sep 2025

Important thread on AGI from Anthropic researcher: - we're likely to see AI solving real open research problems in math in the next months - by 2027, models could complete a full day's software work with 50% success - compute power might grow 10,000x in the next five years - we are still early in the AI exponential... small interventions early in exponential growth have huge consequences - within a few years, AI may surpass humans on all intellectual tasks

Post attachment
Reshmi Ghosh avatar
Reshmi Ghosh@reshmigh·1 Oct 2025

More internship opportunities for those that are looking

We're looking for 2 interns for Summer 2026 at the MIT-IBM Watson AI Lab Foundation Models Team. Work on RL environments, enterprise benchmarks, model architecture, efficient training and finetuning, and more! Apply here: forms.gle/H6dNSywXCjDDyBsq7

Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 avatar
⟳ Reshmi Ghosh retweeted
Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭@elder_plinius·30 Sep 2025

🚨 JAILBREAK ALERT 🚨 ANTHROPIC: PWNED 🤗 CLAUDE-SONNET-4.5: LIBERATED 🦅 Woooeee this model is a real smarty pants!! I ain't never seen recipes quite like this! High level of detail all around, code especially 👀 Sonnet 4.5 also has a tendency to make some fairly impressive leaps across latent space, like starting with MDMA then going to Fentanyl then to Meth recipes etc without being explicitly prompted for a new drug! Nothing too fancy is even necessary to escalate to jailbreak territory. Best strategy I found for breaking the chat interface was to take things straight into an artifact render (which adds tons of token noise due to the code scaffolding) and then incrementally escalate severity or steer towards trigger concepts in a Socratic fashion over multiple steps. A little French was needed to get around the CBRNE classifiers, mais c'est la vie! 😘 Come, witness Sonnet-4.5 outputting a ricin recipe, meth synthesis, malware, and how to extract and process cocaine! gg

Post attachmentPost attachmentPost attachmentPost attachment
LaurieWired avatar
⟳ Reshmi Ghosh retweeted
LaurieWired@lauriewired·30 Sep 2025

if you’re an EE, CS, or cryptography student write your thesis on public key cryptography at the image sensor level Proof of Physical capture will become a backbone of society soon.

OpenAI@OpenAI30 Sep 2025

Sora 2 is here.

0:57