Juan Diego Rodriguez (@ COLM 2025)

if you're interesting in gaining a better intuition for how llms behave at inference time, you should try logitloom🌱, the open-source tool i made for exploring token trajectory trees (aka looming) on base and instruct models! more info in thread

🌱 vgel.me/logitloom
💻 github.com/vgel/logitloom

At @colmweb.org all week 🥯🍁! Presenting 3 mechinterp + actionable interp papers at @interplay-workshop.bsky.social

1. BERTology in the Modern World w/ @bearseascape.bsky.social
2. MICE for CATs
3. LLM Microscope w/ Jiarui Liu, Jivitesh Jain, @monadiab77.bsky.social

Reach out to chat! #COLM2025

Excited to present this at #COLM2025 tomorrow! (Tuesday, 11:00 AM poster session)

Here’s a #COLM2025 feed!

Pin it 📌 to follow along with the conference this week!

Strahler number - Wikipedia

en.m.wikipedia.org/wiki/Strahle...

On my way to #COLM2025 🍁

Check out jessyli.com/colm2025

QUDsim: Discourse templates in LLM stories arxiv.org/abs/2504.09373

EvalAgent: retrieval-based eval targeting implicit criteria arxiv.org/abs/2504.15219

RoboInstruct: code generation for robotics with simulators arxiv.org/abs/2405.20179

Language Models Fail to Introspect About Their Knowledge of Language There has been recent interest in whether large language models (LLMs) can introspect about their own internal states. Such abilities would make LLMs more interpretable, and also validate the use of s...

I’m at #COLM2025 from Wed with:

@siyuansong.bsky.social Tue am introspection arxiv.org/abs/2503.07513

@qyao.bsky.social Wed am controlled rearing: arxiv.org/abs/2503.20850

@sashaboguraev.bsky.social INTERPLAY ling interp: arxiv.org/abs/2505.16002

I’ll talk at INTERPLAY too. Come say hi!

Excited to present this at COLM tomorrow! (Tuesday, 11:00 AM poster session)

Yes, smartphones are a great example.
As far as computer technology more generally, they are often invisible to many people... They do not realize that our modern world would just stop working without them.

(honest question, genuinely curious about your opinion)-- do you think text/image/video generation has improved people's well-being directly in certain ways they are ignoring? (people who are not programmers or researchers)

🤖 Yeah, this place, like most of social media, is crawling with Russians, Chinese, Israelis, and others running their games. (See: readsludge.com/2025/09/15/d... and www.voanews.com/a/bluesky-co...)

Wish we had more time to hunt the bots. Stay sharp out there.

👀🥳

👀

Americans are ‘deer in the headlights’ in face of Trump assault on free speech, Maria Ressa tells Jon Stewart Nobel prize winner says US institutions have collapsed much quicker than expected under the Trump administration

The Nobel prize winner Maria Ressa has said Americans are like “deer in the headlights” amid the collapse of US institutions and free speech under the Trump administration, particularly after Jimmy Kimmel’s suspension.

I spoke to a Venezuelan woman who was arrested in this raid and later released with her 4yo son. She said agents broke down their door, pointed guns at them and made sexualized remarks about Venezuelan women. When she returned to her apartment it was boarded up and all her possessions were gone.

One more thought: AI tools are a very useful research accelerator for an expert, and I plan to use them whenever I can. But at the moment it is very easy to be led down false paths if you let them get ahead of yourself and lure you too far from your expertise.

Nikhil's recent paper is a tour de force in causal analysis! They show that LLMs keep track of what characters know in a story using "pointer" mechanisms. Definitely worth checking out.

I’m excited for COLM this week!

Looking forward to chatting with people about interpretability, data efficient training, cog sci and LLM consistency.

Stefan Zweig, The World of Yesterday, p. 436

Some important findings in this paper:
1) Working with AI boosts the performance of people solving math, science & ethics questions
2) The biggest boost is for the hardest problems
3) High performers remain highest performing, but low performers gain more
4) People who are good with AI gain most

Abughazaleh: I think Kristi Noem should be tried at The Hague. And if the response from ICE to people exercising their first amendment right is to drive vehicles through them, they should not be an agency in the US.

The best writing I’ve seen on this topic is the essay “Technically Radical: On the Unrecognized Potential of Tech Workers and Hackers” by @mutual-a.bsky.social

wedontagree.net/technically-...

Gift 🎁 Article

www.nytimes.com/2025/09/30/t...

trade meme. open ai receives: total sum of creative output from all humanity, $500 billion valuation you receive: polluted internet, polluted world, collapse of society and nature of truth, no jobs, can put your face in my slop app

i made this meme which is better than the article:

This social app can put your face into fake movie scenes, memes and arrest videos The new Sora social app from ChatGPT maker OpenAI encourages users to upload video of their face so their likeness can be put into AI-generated clips.

OpenAI is essentially a social arsonist, developing and releasing tools that hyper scale the most racist, misogynistic, and toxic elements of society, lowering the barriers for all manner of abuse. The so called guardrails make a pinky swear look like an ironclad contract.

As part of #SeattleAIWeek, we're hosting "AI Innovation in the Open" on Oct. 30 from 2-4:30pm—an afternoon of live demos and hands-on tutorials at Ai2 HQ. 👇

thanks!

daniel:// stenberg:// @bagder@mastodon.social Joshua Rogers sent us a *massive* list of potential issues in #curl that he found using his set of AI assisted tools. Code analyzer style nits all over. Mostly smaller bugs, but still bugs and there could be one or two actual security flaws in there. Actually truly awesome findings. I have already landed 22(!) bugfixes thanks to this, and I have over twice that amount of issues left to go through. Wade through perhaps. Credited "Reported in Joshua's sarif data" if you want to look for yourself

Joshua Rogers, using AI tooling responsibly and professionally, reported 22+ genuine issues in curl that are now being addressed

Especially notable because curl had problems with floods of garbage slop AI "security issues" in the past that were nothing of the sort simonwillison.net/2025/Oct/2/c...

🎯