Simon Deltadahl
@deltadahl
Followers
4
Following
8
Media
0
Statuses
19
Neural Nets + Data + Compute = Cool. PhD student @Cambridge_Uni
Cambridge
Joined December 2023
RT @giffmana: Big fat metal boxes cannot & will not ever be able to float in the sky. Metal boxes will be able to roll on the ground when p….
0
60
0
RT @charliermarsh: You can set `UV_TORCH_BACKEND=auto` and uv will automatically install the right CUDA-enabled PyTorch for your machine, z….
0
233
0
RT @NeelNanda5: After supervising 20+ papers, I have highly opinionated views on writing great ML papers. When I entered the field I found….
0
177
0
RT @karpathy: I attended a vibe coding hackathon recently and used the chance to build a web app (with auth, payments, deploy, etc.). I tin….
0
663
0
RT @christiancooper: I asked #R1 to visually explain to me the Pythagorean theorem. This was done in one shot with no errors in less than….
0
487
0
RT @nrehiew_: This figure right here is the single biggest reason why we will never get o1/o3's reasoning traces. The unreasonable effecti….
0
53
0
RT @virattt: Our AI hedge fund now trades multiple stocks. One step closer to a real-world system. Our system has the following:.• valuati….
0
21
0
RT @gordic_aleksa: guys why is this not all over the timelines?. is this cgi or real thing? (eitherway it's impressive lol). when did we go….
0
2
0
RT @JustinLin610: 😓 I almost forgot we released something tonight. Yes, just the base models for Qwen2-VL lah. Not a big deal actually.….
0
134
0
RT @cloneofsimo: U wanted to use @cursor_ai on latex but it doesn't autocompile when saved like overleaf right? here is latex installer +….
0
10
0
RT @CamImaging: Today's seminar featured @deltadahl from @blood_counts presenting a novel diffusion-based approach for blood cell classific….
0
3
0
RT @ylecun: When training a visual encoder with self-supervised learning, we know for a fact that using a decoder with a reconstruction los….
0
123
0
RT @OfficialLoganK: Just had my 3rd wow moment in AI. this time through AI Overview by NotebookLM 🤯
0
168
0
RT @billyuchenlin: Introducing AI2 𝕎𝕚𝕝𝕕𝔹𝕖𝕟𝕔𝕙 ! We aim to benchmark LLMs with challenging tasks from real users in the wild. 🤗 Link: https:/….
0
109
0
RT @_akhaliq: GaLore. Memory-Efficient LLM Training by Gradient Low-Rank Projection. Training Large Language Models (LLMs) presents signifi….
0
159
0
RT @DrJimFan: Career update: I am co-founding a new research group called "GEAR" at NVIDIA, with my long-time friend and collaborator Prof.….
0
454
0