Graph Coloring You Can See
Visual intuition with Python The post Graph Coloring You Can See appeared first on Towards Data Science.
Like
0
Liked
Liked
digitado
About digitado
Posts by :
Gemini 3.1 Flash-Lite
Gemini 3.1 Flash-Lite Google’s latest model is an update to their inexpensive Flash-Lite family. At $0.25/million tokens of input and $1.5/million output this is 1/8th the price of Gemini 3.1 Pro. It supports four different thinking levels, so I had it output four different pelicans: minimal low medium high Tags: google, ai, generative-ai, llms, llm, gemini, llm-pricing, pelican-riding-a-bicycle, llm-release
Like
0
Liked
Liked
![[P] I trained Qwen2.5-1.5b with RLVR (GRPO) vs SFT and compared benchmark performance](https://www.digitado.com.br/wp-content/uploads/2026/03/62xtrlk4hwmg1-k6CjG7-280x140.png "[P] I trained Qwen2.5-1.5b with RLVR (GRPO) vs SFT and compared benchmark performance")
[P] I trained Qwen2.5-1.5b with RLVR (GRPO) vs SFT and compared benchmark performance
Hello everyone. I trained Qwen2.5-1.5B-Instruct with RLVR and SFT on the GSM8K dataset. RLVR boosted math reasoning by +11.9 points. SFT degraded it by -15.2. SFT (Supervised Fine-tuning): Standard next-token prediction training on labeled data. RLVR (Reinforcement Learning with Verifiable Rewards): The training approach behind DeepSeek-R1. The model is reinforced to produce responses that earn higher rewards from a verifiable signal (e.g., correct math answers). This is what enabled models to generate their own chain-of-thought reasoning and led […]
Like
0
Liked
Liked
AI companies are spending millions to thwart this former tech exec’s congressional bid
A tech billionaire-backed super PAC is spending $125 million to undercut candidates pushing for AI regulation. New York’s Alex Bores, a former tech executive himself, is one of them.
Like
0
Liked
Liked
![[P] We made GoodSeed, a pleasant ML experiment tracker](https://www.digitado.com.br/wp-content/uploads/2026/03/yx8gprmyawmg1-b1rJaw-280x140.png "[P] We made GoodSeed, a pleasant ML experiment tracker")
[P] We made GoodSeed, a pleasant ML experiment tracker
GoodSeed v0.3.0 🎉 I and my friend are pleased to announce GoodSeed – a ML experiment tracker which we are now using as a replacement for Neptune. Key Features Simple and fast: Beautiful, clean UI Metric plots: Zoom-based downsampling, smoothing, relative time x axis, fullscreen mode, … Monitoring plots: GPU/CPU usage (both NVIDIA and AMD), memory consumption, GPU power usage Stdout/Stderr monitoring: View your program’s output online. Structured Configs: View your hyperparams and other configs in a filesystem-like […]
Like
0
Liked
Liked
What we can learn from scientific analysis of Renaissance recipes
Forget “eye of newt and toe of frog/wool of bat and tongue of dog.” People in the 16th century were more akin to DIY scientists than Macbeth’s three witches when it came to concocting home remedies for everything from hair loss and toothache, to kidney stones and fungal infections. Medical manuals targeted to the layperson were hugely popular at the time, according to Stefan Hanss, an early modern historian at the University of Manchester in the UK. “Reader-practitioners” […]
Like
0
Liked
Liked
ChatGPT’s new GPT-5.3 Instant model will stop telling you to calm down
The company says the new model will reduce the “cringe” that’s been annoying its users for months.
Like
0
Liked
Liked
Claude Code rolls out a voice mode capability
Anthropic is stepping up its game in the AI coding space with the rollout of Voice Mode in Claude Code.
Like
0
Liked
Liked
There are plenty of great choices if you want to spend less than $15K on an EV
Last time we looked at the used electric vehicle market, it was to see what the options are if you’re spending $10,000 or less. Two solid choices emerged quickly: a BMW i3 if you don’t need much range, and a Chevrolet Bolt if you do. Lots of earlier Nissan Leafs made the list, too, but these had limited range and air-cooled batteries to contend with; we also included an assortment of compliance cars and, perhaps for the very […]
Like
0
Liked
Liked
Learning Demographic-Conditioned Mobility Trajectories with Aggregate Supervision
Human mobility trajectories are widely studied in public health and social science, where different demographic groups exhibit significantly different mobility patterns. However, existing trajectory generation models rarely capture this heterogeneity because most trajectory datasets lack demographic labels. To address this gap in data, we propose ATLAS, a weakly supervised approach for demographic-conditioned trajectory generation using only (i) individual trajectories without demographic labels, (ii) region-level aggregated mobility features, and (iii) region-level demographic compositions from census data. ATLAS trains a […]
Like
0
Liked
Liked