SereneDB vs ClickHouse
We ran 92 search and analytics queries over 100M, 1B and 10B OpenTelemetry logs against ClickHouse 26.8 with its new text index and SereneDB, all on a single instance.
SereneDB Blog20 min read
benchmarks
33 stories
PandaScript vs Puppeteer and Playwright
The same scraping tasks written as PandaScripts and as Puppeteer and Playwright scripts. Nearly identical code, 4x to 17x less memory, and one binary instead of two processes and a protocol.
Lightpanda Blog10 min readSereneDB vs Elasticsearch vs OpenSearch vs CrateDB
We ran 92 search and analytics queries over 100M and 1B OpenTelemetry logs against Elasticsearch 9.5, its new columnar index mode, OpenSearch, CrateDB and SereneDB.
SereneDB Blog20 min readSereneDB vs ParadeDB vs TigerData vs Postgres
We ran 92 search and analytics queries over 100M and 1B OpenTelemetry logs against vanilla Postgres, ParadeDB with pg_search, TigerData with pg_textsearch and SereneDB.
SereneDB Blog24 min readBest AI Models for Agentic Tool Use - August 2026
TL;DR Claude Opus 5 tops independent SWE-bench Verified tracking at 96% - though Anthropic's own launch materials skip that benchmark entirely for custom evals Qwen3.
Awesome Agents Newsletter Blog11 min readGPT-5 mini
Overview GPT-5 mini launched on August 7, 2025, alongside full GPT-5 and a third, smaller GPT-5 nano, giving developers three sizes of the same generation to trade off against cost and latency.
Awesome Agents Newsletter Blog7 min readThis Week: Mind Viruses, Agent Support, and Waste
Three papers landed this week that, read together, sketch out what happens once you stop treating an AI agent as a single system and start treating it as a node in a network.
Awesome Agents Newsletter Blog7 min readSereneDB vs ArangoDB on search performance
One year after we started SereneDB we ran 92 search and analytics queries over 1B OpenTelemetry logs and put the numbers next to ArangoDB to see how far we have come.
SereneDB Blog20 min readInkling: A New Open-Weight 975B MoE with a Few Surprises
Architecture and benchmark notes on Thinking Machines Lab's 975B Inkling MoE, including short convolutions, relative-position bias, training, and effort control.
Sebastian Raschka4 min readLocal Open-Weight LLMs in Coding Harnesses
Short note on trying local open-weight LLMs across Qwen-Code, Codex, and Claude Code harnesses.
Sebastian Raschka1 min readBenchmarking Lightpanda’s native agent
We learned that an agent’s tools matter more than its engine. We rebuilt our tool surface: the MCP is now far faster and more accurate, and a native agent built into the binary is faster still.
Lightpanda Blog10 min readNorth Mini Code and Agentic Coding Benchmarks
Architecture and benchmark notes for North Mini Code, Cohere's 30B-A3B MoE trained for repository, terminal, and code-generation tasks.
Sebastian Raschka6 min readHow should we benchmark Lightpanda for AI agents?
We ran Lightpanda, agent-browser, and browser-use through AssistantBench and GAIA Level 1 with Claude Sonnet 4.6 as the brain. The tool surface mattered more than the engine.
Lightpanda Blog11 min readGroup-by From Scratch
I've found one of the best ways to grow in my scientific coding is to spend time comparing the efficiency of various approaches to implementing particular algorithms that I find useful, in order to build an intuition of the performance of the building blocks of the scientific Python ecosystem.
Python Data Science Handbook by Jake VanderPlas Blog9 min readFast Lomb-Scargle Periodograms in Python
Image source: astroML. Source code here Edit, Spring 2017: For an in-depth guide to the practical use of Lomb-Scargle periodograms, see the paper discussed in A Practical Guide to the Lomb-Scargle Periodogram.
Python Data Science Handbook by Jake VanderPlas Blog17 min read
Showing 33 of 33 stories
You're all caught up.
AiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts