CODE

→ View original post on X — @alphasignalai

Top AI Papers: RL, SFT, Hallucination, FP4 Quantization

By

@alphasignalai

–

03 February 2025 13h00

Top AI Papers you Can't miss from last Week: We summarized everything from RL vs. SFT training, Hallucination Mitigation with Multi-agent systems, Microsoft's New FP4 Quantization, and more. Here's everything you need to know:

→ View original post on X — @waitin4agi_

Using o1 as Reward Model for Output Selection

By

@waitin4agi_

–

03 February 2025 9h17

The code here yes, but concept is likely. It is quite likely they used o1 as a reward model/critic to choose from a group of outputs

Building an LLM Council with Debate and ELO-Based Chair Selection

By

–

03 February 2025 2h08

This is cool! I want to build something like it too because I want my LLM council. First they all run, then they debate, and then the chair of the council (the highest ELO model) works out the final response.

→ View original post on X — @terence_mills

10 Key Ways Software Engineers Are Using AI

By

@terence_mills

–

03 February 2025 1h00

10 Key Ways Software Engineers Are Using AI
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @lexfridman @sama @kaifulee @ID_AA_Carmack @karpathy @2morrowknight @ylecun

Building a Real-Time Battleship Game Between Two LLMs

By

–

03 February 2025 0h54

Earlier, also ~hour of vibe coding, I built a Battleship game wired up so that you see two LLMs (any two models you select) are fighting each other in real time. I don't have super strong stats yet on this but I believe 4o beats 4o-mini, lol.

Custom LLM Reader App for Interactive Book Analysis

By

–

03 February 2025 0h52

Last ~hour I built a custom LLM reader app so while I read Wealth of Nations I can ask questions about any paragraph. When you click a paragraph and "Ask" it calls an LLM, builds context window of what this is, copy pastes the full chapter, the paragraph, and the question. Works

The Spectrum of LLM Assistance in Programming: From Traditional to Vibe Coding

By

–

03 February 2025 0h22

The amount of LLM assist you receive is clearly some kind of a slider. All the way on the left you have programming as it existed ~3 years ago. All the way on the right you have vibe coding. Even vibe coding hasn't reached its final form yet. I'm still doing way too much.

Vibe Coding: Embracing AI-Powered Development Without Traditional Constraints

By

–

03 February 2025 0h17

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper