Johnny Devriese

AI Engineer 🤖2 wheeled enthusiast 🚲 pizzaiolo 🍕 | AI @stanford 🌲physics @wsu 🐆

[Johnny Devriese @johnnydevriese]

@kepano was excited about this but seems like it's not working

[Stephan Rabanser @steverab]

📣 Excited to share my first work @Princeton : 𝗧𝗼𝘄𝗮𝗿𝗱𝘀 𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗼𝗳 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗥𝗲𝗹𝗶𝗮𝗯𝗶𝗹𝗶𝘁𝘆

AI agents keep getting more capable. But are they actually reliable?

📄 Paper: https://t.co/1CvygFLdct
📊 Dashboard: https://t.co/C1EfoMyaS8

🧵👇

[Denny Zhou @denny_zhou]

Slides for my lecture “LLM Reasoning” at Stanford CS 25: https://t.co/eApGUHyIDo

Key points:
1. Reasoning in LLMs simply means generating a sequence of intermediate tokens before producing the final answer. Whether this resembles human reasoning is irrelevant. The crucial insight is that transformer models can become nearly arbitrarily powerful by generating many intermediate tokens, without the need of scaling the model size (https://t.co/HO2seV6vVl).

2. Pretrained models, even without any fine-tuning, are capable of reasoning. The challenge is that reasoning-based outputs often don’t appear at the top of the output distribution, so standard greedy decoding fails to surface them (https://t.co/75h2QQzT9M)

3. Prompting techniques (e.g., chain-of-thought prompting or "let’s think step by step") and supervised finetuning were commonly used to elicit reasoning. Now, RL finetuning has emerged as the most powerful method. This trick was independently discovered by several labs. At Google, credit goes to Jonathan Lai on my team. Based on our theory ( see point 1), scaling RL should focus on generating long responses rather than something else.

4. LLM reasoning can be hugely improved by generating multiple responses and then aggregating them, rather than relying on a single response (https://t.co/BA5MUzg3PR).

[ₕₐₘₚₜₒₙ @hamptonism]

rebranding Linear Algebra as Artificial Intelligence was the most successful marketing campaign of all time.

[Johnny Devriese @johnnydevriese]

Well Claude Sonnet can't do Jackson E&M problems. So I think physics grad students continue to get to suffer.

[Mihai Simion @faustocoppi60]

Will Barta WINS the last stage of @VueltaCV , his first professional victory after a heroic 50 km solo attack from the breakaway! One of my favourite Movistar victories EVER. Huge congrats, @willbarta ! 👏 #75VCV

[Johnny Devriese @johnnydevriese]

Thought it was april 1st. LFG!!

[Scuderia Ferrari HP @ScuderiaFerrari]

Team Statement

Scuderia Ferrari is pleased to announce that Lewis Hamilton will be joining the team in 2025, on a multi-year contract.

[Johnny Devriese @johnnydevriese]

By far the most important issue on GH https://t.co/dZJ7IGsro4

[Johnny Devriese @johnnydevriese]

Really need an extension that redirects all medium articles to https://t.co/jcnzuPZF2m:<URL>

[Séb Krier @sebkrier]

The DoD gets it! https://t.co/Mc32zzCHHA

[Johnny Devriese @johnnydevriese]

excited to try out dino https://t.co/tuTQz3BfkT

[Johnny Devriese @johnnydevriese]

#Ideogram is amazing

[Johnny Devriese @johnnydevriese]

Kinda funny that FB has kept facebookresearch on GH because someone else already has their username https://t.co/y6TozMcmhJ

[Johnny Devriese @johnnydevriese]

This is a cool way to visualize decision tree splits. https://t.co/ZA2sWksbzV

[Johnny Devriese @johnnydevriese]

Multimodal learning is really cool. CMU also has an excellent course on the topic https://t.co/YZhJs37hK0

[Chip Huyen @chipro]

Open challenges in LLM research

The first two challenges, hallucinations and context learning, are probably the most talked about today.

I’m the most excited about 3 (multimodality), 5 (new architecture), and 6 (GPU alternatives).

Number 5 and number 6, new architectures and new hardware, are very challenging, but are inevitable with time. Because of the symbiosis between architecture and hardware – new architecture will need to be optimized for common hardware, and hardware will need to support common architecture – they might be solved by the same company.

I referenced a lot of papers here, but I have no doubt that I still missed a ton. If there’s something you think I missed, please let me know!

https://t.co/Al2b2Zjqb7

[Ian Tracey @ian_dot_so]

Oppenheimer didn’t need Jira or a certified scrum master

[Johnny Devriese @johnnydevriese]

I don't think Shafer Butte is 7950 ft @BOGUSBASIN https://t.co/pjPkiJaUvd 🧐

[Johnny Devriese @johnnydevriese]

Are RNNs even still a thing? 🫠

[Ferrari Hypercar @FerrariHypercar]

Here’s how the first #WEC grid of the season shapes up for tomorrow’s race 🤩

#️⃣5️⃣0️⃣ - P1
#️⃣5️⃣1️⃣ - P4

#FerrariHypercar #Ferrari499P 🇺🇸 #1000MSebring