Reshmi Ghosh

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

[Reshmi Ghosh @reshmigh]

🚨New paper! With @UMassAmherst , @UofMaryland:
"Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis"🤯.
Why do #reasoningmodels break down when chaining multiple steps? We studied #CoT traces to find out.
🧵(1/n)
🔗https://t.co/upzlb39m3n

[Hua Shen✨ @huashen218]

🧐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: https://t.co/oN2p9yciqY (WiNLP Workshop)
2️⃣ Mind the Value–Action Gap: https://t.co/TGi8oZ1RSl (Main Track)
🔍 Dataset & Code: https://t.co/CxTfTNiMVF

🌱 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): https://t.co/wjazsiwub8

💜 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: https://t.co/1XvgLfPKMl
🔗Tutorial on Spoken Conversational Agents: https://t.co/rpVYqwXxBq

💗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

[Reshmi Ghosh @reshmigh]

So Agents are flat earthers? :D

[Can Vardar @icanvardar]

finally, linkedin is funny

[Tim Althoff @timalthoff]

(please reshare) I'm recruiting multiple PhD students and Postdocs @uwcse @uwnlp
(https://t.co/I5wQsFnCLL). Focus areas incl. psychosocial AI simulation and safety, Human-AI collaboration.

PhD: https://t.co/ku40wCrpYh

Postdocs: https://t.co/K9HUIPJ5h6

[Myra Deng @myra_deng]

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.

[Lily Xu @lilyxu0]

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

[Reshmi Ghosh @reshmigh]

@AmyPrb Prompt Injection is very much an industry/practical use of AI problem!!

[Reshmi Ghosh @reshmigh]

Evaluations.....

[Kyunghyun Cho @kchonyc]

wow

[Niloofar @niloofar_mire]

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 @reshmigh]

It is an infinite glitch circle now!

[Ahmad Beirami @abeirami]

@nmboffi 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 @sarahmsachs]

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…

[Reshmi Ghosh @reshmigh]

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

[Haider. @haider1]

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

[Reshmi Ghosh @reshmigh]

More internship opportunities for those that are looking

[Shawn Tan @tanshawn]

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: https://t.co/hS2meJm9j4

[Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭 @elder_plinius]

🚨 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

[LaurieWired @lauriewired]

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.

[vas @vasuman]

Claude 4.5 Sonnet just refactored my entire codebase in one call.

25 tool invocations. 3,000+ new lines. 12 brand new files.

It modularized everything. Broke up monoliths. Cleaned up spaghetti.

None of it worked.
But boy was it beautiful.

[Reshmi Ghosh @reshmigh]

Hear hear Interns

[Yunyao Li @yunyao_li]

🚀 I'm hiring 2026 Applied Scientist / ML Engineering Interns to push the frontier of multi-agent AI for the enterprise.

💡 Research NLU, generative & agent-based AI, machine learning
⚡ Build scalable models, benchmark datasets & metrics
🤝 Create impactful solutions for publication and production
⭐️ Full-time conversion opportunities for PhD / MS students graduating in late 2026 / mid-2027
🔗 [Apply Now] https://t.co/r9oFORCRw0

#AI #MachineLearning #Internship #Adobe

[Kushan Mitra @kushanmitra]

Vah, pothole alerts built in to @atherenergy maps for multiple cities

[ℏεsam @Hesamation]

ML interview question: why do embeddings come in 768 or 1024?

- “because BERT did it”
- “because of GPU optimization”

BUT WHY?!

The replies under this post is everything wrong with current courses and blog posts: superficiality.

this isn’t reasoning, it’s memorization

[Reshmi Ghosh @reshmigh]

@TWhidden I think it is resolved now :) I am able to use it

[Reshmi Ghosh @reshmigh]

@abeirami The founders will make sure there is “no bureaucracy”. lol that line took me out