Towards Data Science
Jun 19
Python 3.14 and its New JIT Compiler
A technical overview and some benchmarks The post Python 3. 14 and its New JIT Compiler appeared first on Towards Data Science .
I Reran My Python 3.14 JIT Benchmarks on Python 3.15
The article reports that the author reran Python 3.14 JIT benchmarks on Python 3.15, observing a significantly stronger Just-In-Time (JIT) performance across the same three workloads. However, the improved JIT does not universally benefit all programs, indicating that performance gains are workload‑dependent.
Related stories
Simon Willison
Oct 13
web-edit 0.1a1
The article announces the release of web-edit version 0.1a1. It highlights performance optimizations that were written by Claude Opus 5.5, which were generated after feeding it a Python 3.15 profiling report created by GPT‑6 Astra. The release is tagged with "profiling" and "projects".
Simon Willison
Aug 25
EVE Online: The Move to Python 3 Begins!
EVE Online is beginning its transition to Python 3, a move that will involve using the futurize script on 2.4 million lines of code and a manual review of about 20,000 differences between Python 2 and Python 3. The company has historically run on Stackless Python since 2003, with the last major upgrade in 2010 to Stackless Python 2.7. While the announcement does not detail how Stackless will be replaced, the team previously showcased a shift away from Stackless in their Carbon engine for EVE Frontier, leveraging the open‑source carbonengine/scheduler library.
Towards Data Science
Jun 13
Larger Context Windows Don’t Fix RAG — So I Built a System That Does
Increasing context size in RAG systems doesn’t improve accuracy for aggregation tasks—it makes errors harder to detect. In this article, I benchmark retrieval-based pipelines against a deterministic full-scan engine across 100,000 rows and show why computation queries must be routed away from RAG entirely.
arXiv AI
Jun 30
SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
arXiv:2511. 06090v3 Announce Type: replace-cross Abstract: Optimizing the performance of large-scale software repositories demands expertise in code reasoning and software engineering (SWE) to reduce runtime while preserving program correctness.
Simon Willison
Sep 1
Python 3.15.0 candidate 2 is here!
Python 3.15.0 candidate 2 has been released, marking the final release candidate for the upcoming 3.15 release scheduled for October. Hugo van Kemenade, the release manager, notes that only clear bug‑fix changes are allowed between this candidate and the final release, and urges third‑party maintainers to prepare wheels on PyPI and test their projects during this phase. The new RC is not yet available for GitHub Actions, but users can add it to their testing matrix using the allow‑prereleases and check‑latest flags to automatically test against the latest RC and then the stable release.
Towards Data Science
Oct 24
Python 3.15 Has a New Profiler
The article discusses the new profiler introduced in Python 3.15, highlighting its capabilities compared to the existing cProfile tool. It explains what the new profiler can detect that cProfile misses, providing insights into performance analysis improvements. The post was originally published on Towards Data Science.
Simon Willison
Aug 24
llm-anthropic 0.27
The release of llm‑anthropic 0.27 updates the Anthropic plugin for LLM to be compatible with the newly released anthropic v1.0.0 Python library, which has switched from httpx to httpx2. This mirrors a similar change made by OpenAI in their v3.0.0 release two weeks prior. The update includes a migration guide and a pull request that ensures tests pass after upgrading to anthropic>=1.
Simon Willison
Oct 10
Python 3.15.0 added to actions/python-versions
Python 3.15.0 has been added to the actions/python-versions repository. The author had been monitoring the repository for the release and used ChatGPT to automate the check. With the new version available, users can now include "3.15" in their GitHub Actions testing matrix to run tests against the latest Python release.
Towards Data Science
Oct 26
Claude Code vs. Cursor: What a Field Test Shows That the Feature Comparisons Miss
The article compares Claude Code and Cursor by presenting a field test that reveals differing token usage: one benchmark shows Claude Code using 33,000 tokens versus Cursor’s 188,000, while another benchmark shows the opposite. The post aims to provide a definitive comparison for teams deciding between the two tools.
arXiv AI
Sep 10
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
arXiv:2609.07008v1 Announce Type: new Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it...
arXiv Computation and Language
Oct 15
T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration
arXiv:2605.29054v3 Announce Type: replace-cross Abstract: Migrating a machine-learning codebase across frameworks--for example from PyTorch to JAX--is a routine but costly engineering task that is fu...