DEV Community

Machine Learning

A branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Beyond Static Weights: The Emergence of Liquid Neural Networks (LNNs)

Beyond Static Weights: The Emergence of Liquid Neural Networks (LNNs)

Comments
2 min read
Ten of 45 models lose to "pick the longest answer" on 656 MMLU-Pro questions

Ten of 45 models lose to "pick the longest answer" on 656 MMLU-Pro questions

Comments
4 min read
Thompson Sampling: Why Randomised Exploration Beats Greedy Optimisation

Thompson Sampling: Why Randomised Exploration Beats Greedy Optimisation

Comments
7 min read
NyoomFloat12: How a 12-Bit Fixed-Length Format Doubles LLM Inference Throughput Without Losing a Single Bit

NyoomFloat12: How a 12-Bit Fixed-Length Format Doubles LLM Inference Throughput Without Losing a Single Bit

Comments
5 min read
Kimi K3.1 Pro: A 2.8T Open-Weight Model That Nearly Matches Claude Opus 5.5 on Coding

Kimi K3.1 Pro: A 2.8T Open-Weight Model That Nearly Matches Claude Opus 5.5 on Coding

Comments
3 min read
Open Weights, Hidden Payloads: How to Download and Load LLM Models Without Getting Owned

Open Weights, Hidden Payloads: How to Download and Load LLM Models Without Getting Owned

Comments
7 min read
An Open AI Prompt Library: 2,600 Image and Video Prompts You Can Download as a Dataset

An Open AI Prompt Library: 2,600 Image and Video Prompts You Can Download as a Dataset

Comments
3 min read
How I built a CI-safe eval harness for structured LLM output

How I built a CI-safe eval harness for structured LLM output

Comments
1 min read
One Worker With AI Could Do 10 Jobs Zoho Founder Warns

One Worker With AI Could Do 10 Jobs Zoho Founder Warns

Comments
2 min read
Gemini 4 Carbon vs Claude Opus 5.5: #1 Overall, but Opus Still Wins at Coding

Gemini 4 Carbon vs Claude Opus 5.5: #1 Overall, but Opus Still Wins at Coding

Comments 3
7 min read
Models follow MMLU-Pro's longest-answer cue too, and three score below it

Models follow MMLU-Pro's longest-answer cue too, and three score below it

Comments
4 min read
The Mean Lied: How a Second Statistic Fixed Long-Context Memory

The Mean Lied: How a Second Statistic Fixed Long-Context Memory

Comments
6 min read
Building Reliable AI-Powered Predictive Maintenance Systems: Beyond Anomaly Detection

Building Reliable AI-Powered Predictive Maintenance Systems: Beyond Anomaly Detection

Comments
5 min read
A 2.6B model on an iPhone that always answers in valid JSON

A 2.6B model on an iPhone that always answers in valid JSON

Comments 1
3 min read
A "neuron-derived" video model launched today - the neurons stay in the lab, so what are you buying?

A "neuron-derived" video model launched today - the neurons stay in the lab, so what are you buying?

Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.