Latest #llm Threads 
If you’re underwhelmed with AI coding agents or simply want to get more out of them, give parallelization a try. After seeing the results...
New
One common practice for working with MCP tools calls is to put the outputs from a tool back into the LLM as a message, and ask the LLM fo...
New
CocoIndex now supports knowledge graph with incremental processing. Build live knowledge for agents is super easy with CocoIndex!
New
But for what I do use LLMs for, it’s invaluable.
New
A misconfiguration that might have cost us $7,000
New
In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost i...
New
Open Euro LLM.
A series of foundation models for transparent AI in Europe
New
My LLM codegen workflow atm.
A detailed walkthrough of my current workflow for using LLms to build software, from brainstorming through ...
New
Episode 239 of Thinking Elixir. News includes an impressive case study from Remote showing how they scaled Elixir to support nearly 300 e...
New
OpenAI o3-mini, now available in LLM.
OpenAI’s o3-mini is out today. As with other o-series models it’s a slightly difficult one to eval...
New
This Week's Trending
If you’re underwhelmed with AI coding agents or simply want to get more out of them, give parallelization a try. After seeing the results...
New
This Month's Trending
But for what I do use LLMs for, it’s invaluable.
New
CocoIndex now supports knowledge graph with incremental processing. Build live knowledge for agents is super easy with CocoIndex!
New
One common practice for working with MCP tools calls is to put the outputs from a tool back into the LLM as a message, and ask the LLM fo...
New
This Year's Trending
Loads of news stories about DeepSeek here in the last few days, no surprise as it’s been making headlines across the world! Currently a h...
New
AMD’s MI300X Outperforms NVIDIA’s H100 for LLM Inference.
Discover if AMD’s MI300X accelerator can outperform NVIDIA’s H100 in real-worl...
New
Hello Qwen2.
GITHUB HUGGING FACE MODELSCOPE DEMO DISCORD
Introduction After months of efforts, we are pleased to announce the evolution...
New
Alex Strick van Linschoten - How to think about creating a dataset for LLM finetuning evaluation.
I summarise the kinds of evaluations t...
New
Use Prolog to improve LLM’s reasoning.
On one side, LLMs show unseen capabilities in reasoning, but on the other - reasoning in LLMs is ...
New
In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost i...
New
How to run an LLM locally on your PC in less than 10 minutes.
Cut through the hype, keep your data private, find out what all the fuss i...
New
A misconfiguration that might have cost us $7,000
New
Top 9 Libraries to Accelerate LLM Building.
The Open-source Tool Stack to build, scale, test, deploy, and monitor LLMs in 2024.
New
Offline Reinforcement Learning for LLM Multi-Step Reasoning.
Improving the multi-step reasoning ability of large language models (LLMs) ...
New
My LLM codegen workflow atm.
A detailed walkthrough of my current workflow for using LLms to build software, from brainstorming through ...
New
GitHub - NVIDIA/garak: the LLM vulnerability scanner.
the LLM vulnerability scanner. Contribute to NVIDIA/garak development by creating ...
New
Episode 239 of Thinking Elixir. News includes an impressive case study from Remote showing how they scaled Elixir to support nearly 300 e...
New
GitHub - samuel-vitorino/lm.rs: Minimal LLM inference in Rust.
Minimal LLM inference in Rust. Contribute to samuel-vitorino/lm.rs develo...
New
Forest Friends Zine.
A guide for AI Engineers building the wild world of LLM system evals
New
Last Three Year's Trending
Self-Retrieval: Building an Information Retrieval System with One Large Language Model.
The rise of large language models (LLMs) has tra...
New
Code LoRA from Scratch - a Lightning Studio by sebastian.
LoRA (Low-Rank Adaptation) is a popular technique to finetune LLMs more effici...
New
GitHub - intel-analytics/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma...
New
GitHub - rasbt/LLMs-from-scratch: Implementing a ChatGPT-like LLM from scratch, step by step.
Implementing a ChatGPT-like LLM from scrat...
New
Jamba: A Hybrid Transformer-Mamba Language Model.
We present Jamba, a new base large language model based on a novel hybrid Transformer-...
New
Hello from Scrapegraph-ai | Scrapegraph-ai.
Official documentation of Scrapegraph-ai
New
Episode 185 of Thinking Elixir. Dive into the world of structured LLM prompting with our latest guest who shares insights on their innova...
New
Home | ArtificialAnalysis.ai.
Analysis of AI models and hosting providers - choose the best model and provider for your use case
New
GitHub - google-deepmind/recurrentgemma: Open weights language model from Google DeepMind, based on Griffin…
Open weights language model...
New
Kindllm - LLM chat for Kindle.
The distraction-free LLM chat app for Kindle
New
Building an early warning system for LLM-aided biological threat creation.
We’re developing a blueprint for evaluating the risk that a l...
New
Get consistent data from your LLM with JSON Schema.
How to parse content from a tool that is made to speak in human sentences.
New
A big barrier to getting started with local AI development is access to hardware. And by “local”, I mean having direct access to a GPU an...
New
LLM inference speed of light.
In the process of working on calm, a minimal from-scratch fast CUDA implementation of transformer-based la...
New
What would an LLM OS look like?.
Andrej Karpathy’s YouTube channel is fantasic. He just published an Intro to Large Language Models vide...
New
Trending Over Three Years
Aya.
Cohere’s non-profit research lab, C4AI, released the Aya model, a state-of-the-art, open source, massively multilingual, research L...
New
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.
In this work, we discuss building performant Multimodal Large La...
New
DRINK ME: (Ab)Using a LLM to compress text.
Introduction
Large language models are trained on huge datasets of text to learn the relat...
New
Extracting Social Support and Social Isolation Information from Clinical Psychiatry Notes: Comparing a Rule-based NLP System and a Large ...
New
GitHub - apple/ml-mgie.
Contribute to apple/ml-mgie development by creating an account on GitHub.
New
GitHub - google/maxtext: A simple, performant and scalable Jax LLM!.
A simple, performant and scalable Jax LLM! Contribute to google/max...
New
From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples.
We analyze how well pre...
New
Can GPT Optimize My Taxes?.
TL;DR Yep.
New
Wikipedia Citation Needed.
A chrome extension for finding citations in Wikipedia by using ChatGPT
New
New
A new Go blog post/announcement has been posted!
Get the full details here: Building LLM-powered applications in Go - The Go Programmin...
New
Rethinking LLM Inference: Why Developer AI Needs a Different Approach.
A technical blog post from Augment Code explaining their approach...
New
Episode 228 of Thinking Elixir. News includes Theo releasing his ElixirConf presentation video on his channel, the launch of the Gleam an...
New
OpenAI o3-mini, now available in LLM.
OpenAI’s o3-mini is out today. As with other o-series models it’s a slightly difficult one to eval...
New
Does your LLM truly unlearn? An embarrassingly simple approach to recover unlearned knowledge.
Large language models (LLMs) have shown r...
New
Get money off!
The Pragmatic Bookshelf
35% off any eBook
Manning Publications
45% off any item
The Pragmatic Studio
20% off any course
Simply use coupon code "devtalk.com" at checkout. Where applicable this coupon can be used for an many items and as many times as you like!
Filter by Type:
Popular Tags
- #apple
- #code
- #programming
- #linux
- #web
- #podcasts
- #blog-post
- #video
- #news
- #otp
- #community
- #chatgpt
- #new
- #macos
- #microsoft
- #learning
- #openai
- #github
- #database
- #development
- #design
- #ios
- #performance
- #testing
- #project
- #internet
- #apps
- #css
- #hardware
- #android
- #quantum
- #guide
- #nvidia
- #intel
- #amazon
- #browser
- #liveview
- #manning
- #musk
- #privacy
- #social
- #languages
- #windows
- #api
- #writing
- #games
- #tiktok
- #ai
Popular Portals
- /elixir
- /rust
- /wasm
- /ruby
- /erlang
- /phoenix
- /keyboards
- /rails
- /js
- /python
- /security
- /go
- /swift
- /vim
- /clojure
- /java
- /haskell
- /emacs
- /svelte
- /onivim
- /typescript
- /crystal
- /c-plus-plus
- /tailwind
- /kotlin
- /gleam
- /react
- /flutter
- /elm
- /ocaml
- /ash
- /vscode
- /opensuse
- /centos
- /php
- /deepseek
- /html
- /zig
- /scala
- /debian
- /nixos
- /lisp
- /agda
- /react-native
- /sublime-text
- /textmate
- /kubuntu
- /arch-linux
- /ubuntu
- /revery
Devtalk Sponsors
Practical resources that improve the lives of professional developers.
We build trusted fault-tolerant systems that scale to billions of users.
Real-time error tracking, performance insights, and observability for devs.
Develop your skills with books, videos, and courses.
Catch errors, track performance, monitor hosts and more.
Enabling companies to succeed by building software people love.
Courses that'll move you from confusion to "Aha, now I get it!"