13 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"
RAG Series (3): Tuning These 4 Parameters to Go From 'It Works' to 'It Works Well'
Why Does Your RAG Give Wrong Answers When Someone Else's Doesn't? In the first two articles, we built a RAG pipeline that runs. But many people find that while the code works, answ…
Christophe Pettus: All Your GUCs in a Row: autovacuum
Disable autovacuum and PostgreSQL will cheerfully show you every failure mode in its playbook, from table bloat to transaction ID wraparound.…
Fine-tuning My Terraform Exam Prep with Practice Exams
Day 29 of my 30-Day Terraform Challenge was focused on exam readiness. There was no new...…
Liberty Notebook: Chris DeMarco, players talk fine tuning offense, team’s $600 million valuation & more
Sunday’s preseason matchup against the Connecticut Sun will be the final live opportunity for the Liberty to fine tune its offense before the start of the regular season. In last w…
Oxford study: ‘Friendly’ AI chatbots are less accurate, more sycophantic
Oxford Internet Institute research shows warm-tuned AI models make more mistakes and reinforce misconceptions.…
Math-English Hybrid Notation: A Tool for Tuning LLM Register
I built an AI chat app for fun, but as I developed, I started getting quite serious about building prompt-testing instruments / CLI tools so that Claude Code could run serious prom…
Finetuning Dataset: Claude Opus 4.6/4.7 - 8.7k Chats
A synthetic fine-tuning dataset created from Claude 4.6/4.7. 8,706 total examples all with reasoning. I haven't reviewed the data but there was some basic cleaning applied. Refusal…
Linux network tuning: TCP BBR, NIC ring buffers, and SFTP throughput
SFTP capped at 800 KB/s on a Gbit link. CUBIC, default ring buffers, misconfigured socket buffers — five kernel and daemon tweaks that bring throughput from 800 KB/s to several MB/…
Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs
The official code repo of Alignment Whack-a-Mole: Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models - cauchy221/Alignment-Whack-a-Mole-Code…
Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for adapting large language models (LLMs). In this work we challenge the wide-spread assumption that parameter effici…
Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning
With the accumulation of resources in the era of big data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different…
Sources and memos: Tencent employees used Claude Code to assist them with evaluating and fine-tuning the company's new Hy3 model to improve its performance (Juro Osawa/The Information)
By Juro Osawa / The Information. View the full context on Techmeme.…
Going from 3B/7B dense to Nemotron 3 Nano (hybrid Mamba-MoE) for multi-task reasoning — what changes in the fine-tuning playbook? [D]
Following up on something I posted a few days back about fine-tuning for multi-task reasoning. Read a lot since then, and I've moved past the dense 3B vs 7B question — landing on N…