51 stories tagged with #tuning, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Tuning"
Fine-tuning an LLM to write docs like it's 1995
In my predictions for 2030 I wrote that tech writers would be using specialized LLMs, running locally on powerful hardware. I see hints of this move to “local first” among engineer…
Extract More Kernel Performance with Nvidia CompileIQ Auto-Tuning
NVIDIA CompileIQ tackles one of the hardest problems in performance engineering: finding the compiler options that unlock the best performance for a specific workload. Consider a t…
Show HN: Self tuning chat exposing it's semantic and agentic cache
Open-source RAG chatbot over Valkey, Redis OSS, Dragonfly, and BetterDB docs. Live demo of @betterdb/agent-cache and @betterdb/semantic-cache with real-time hit/miss metrics.…
Using Claude Cowork for installing and finetuning
Fine-Tuning Qwen2.5-0.5B to Write SRE Post-Mortem Summaries
Writing post-mortem root-cause summaries is time-consuming and inconsistent. Junior SREs miss...…
DuckDB 1.5.3 Iceberg updates, PostgreSQL TDE extension & AI index tuning
DuckDB 1.5.3 Iceberg updates, PostgreSQL TDE extension & AI index tuning ...…
Uploaded my Qwen3.6 27B based fine tune, after two years of experience fine tuning models
Canadian filmmaker Daniel Roher is fine-tuning his career, but hasn’t forgotten about Navalny
Toronto-born filmmaker Roher is an irrepressible dynamo of energy…
Magento 2 Nginx Optimization for High Traffic — Complete Server Tuning Guide
Tune Nginx for Magento 2 to handle high traffic without breaking a sweat. Worker processes, gzip, keepalive, microcaching, SSL/TLS, and more — all with real config examples.…
Just Tuning In? Here’s What to Know About the Midterms.
I tested 4 methods to make LLMs write literary subtext. Few-shot with 5 examples beat fine-tuning and DPO.
Contrastive Decoding Diffing: Recovering Finetuning Data Without Weight Access
Narrowly finetuned language models memorize implanted content verbatim, but auditing what a deployed model has been taught, without access to its weights or training data, remains …
RAG vs Fine-Tuning- Choosing Right Strategy for Modern AI Applications
AI applications go beyond conversational chatbots and general use cases. Companies want their AI...…
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown…
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
While general-purpose Large Language Models (LLMs) applied to Geology often hallucinate when reasoning about subsurface structures and deep-time evolution, current AI in Earth scie…
Tuning into quantum sounds: Acoustic devices simplify quantum sensors
Please give me your best tips for fine tuning RTX Pro 6000 on Intel i7-14700KF
Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning
Recent advancements in instructional fine-tuning have injected noise into embeddings, with NEFTune (Jain et al., 2024) setting benchmarks using uniform noise. Despite NEFTune's emp…
How does your MSSP handle fine-tuning detection rules for false positives? (e.g. "Guest" policy hitting UDP/TCP scan alerts) — do you verify with the customer before suppressing?
AI-Native Database: Scalable Performance, Autonomous Tuning & Vector Search
Modern applications generate massive amounts of data every second. Traditional database systems struggle to keep pace with these demands. Performance…
The php-fpm Tuning Cheat Sheet: 5 Settings That Decide Your p99
php-fpm has 30+ knobs. Five of them decide your p99. The other 25 don't matter until you've got the five right. Real www.conf snippets inside.…
PID Tuning That Actually Converges: Ziegler-Nichols and the Root Locus View
The PID controller is the workhorse of industrial control. It runs temperature loops, motor drives,...…
PostgreSQL 17 migration postmortem - (WAL recycling, replication lag, silent timeouts, and conservative tuning gone wrong)
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
Recent large language models support inputs of up to 10 million tokens, yet they perform poorly on long-context tasks that require complex reasoning. Such tasks can be solved using…
Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon, known as catastrophic forget…
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually en…
Christophe Pettus: All Your GUCs in a Row: checkpoint_timeout and checkpoint_completion_target
PostgreSQL's default 5-minute checkpoint interval wastes I/O on modern servers.…
Stop tuning multi-agent prompts by hand: Learning prompts via system-level credit assignment (CANTANTE)
The Free Note Frequency Chart: A Practical Guide to Understanding Pitch and Tuning
Explore how a free note frequency chart bridges music theory and physics. This article explains note...…
Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step …
US Catholic converts are tuning out their liberal, heterodox bishops
Pope Francis' brand of Catholicism, now continuing under Pope Leo XIV, is a politicized version of the faith that prioritizes wokeness and social justice over doctrinal fidelity.…
Fine-Tuning Llama 3.2 3B on Medical QA: Week 1 Setup and Baseline Inference
The Problem With General-Purpose LLMs in Healthcare Ask a general-purpose LLM about the...…
Fixing LLM Writing with Distribution Fine Tuning
Technical Report: How Distribution Fine Tuning (DFT) improves LLM writing quality…
Distribution Fine Tuning (DFT): A post training step that fixes LLM writing
I fixed why LLMs write so poorly, and I have a demo to prove it Announcing Distribution Fine Tuning (DFT): A post training step that fixes LLM writing Model outputs fooled pangra…
Just Tuning In? Here’s What to Know. - The New York Times
Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.…
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
A Blog post by NVIDIA on Hugging Face…
Show HN: Dataset for AI training and fine tuning
Article 10 and Annex IV-ready CC0 training data for EU high-risk AI compliance. IP indemnity included on Compliance tier. Enforcement starts 2 August 2026.…
RAG vs. Fine-Tuning – The Question Every AI Builder Gets Wrong
AI models don't know your private data. Two approaches have been the standard answer. In 2026, a third matters just as much.…
Representation Without Reward: A JEPA Audit for LLM Fine-Tuning
Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outp…
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor discovery plays a central rol…
$f$-Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
In GFlowNets and variational inference, it has been shown that the mean square error between target and model log probabilities is an effective, low variance, surrogate loss for tr…
Tuning-free Instruction-based Video Editing Via Structural Noise Initialization and Guidance
Video editing poses a significant challenge. While a series of tuning-free methods circumvent the need for extensive data collection and model training, they often underutilize the…
The LLM Fine-Tuning Guide
From dataset to GGUF - every parameter explained, every step runnable…
Reducing LLM Hallucinations in 2026: LoRA, F-DPO, and the Math That Actually Works
It is May 2026, and the field has stopped pretending hallucinations are going to disappear. What...…
LLMs as Linguistic Probes: A Graduate Student's Guide to Advanced Syntax, Semantics, and Efficient Fine-Tuning
The intersection of large language models (LLMs) and advanced linguistics has moved beyond...…
Agentic LLM Inference Parameters Reference for Qwen and Gemma
This page is a practical reference for agentic LLM inference tuning (temperature, top_p, top_k,...…
Zhengkid/AutoTTS: Agentic Discovery for Test-Time Scaling
The offical repo for "LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling" - zhengkid/AutoTTS…
I change these two simple settings on my GPU to unlock better performance
Squeeze a bit more juice out of your GPU with two easy changes.…
84. Fine-Tuning LLMs: Teaching Giants New Tricks
GPT-3 has 175 billion parameters. Full fine-tuning updates all 175 billion with every gradient step....…
Mansory Debuts the Ultra-Luxury Zeekr 9X at Auto China 2026
The plug-in hybrid SUV gains a carbon fiber widebody, suicide doors and a plush white leather cabin with an integrated refrigerator.…