---
title: "#python articles | Hashnode"
description: "Python is an interpreted, object-oriented, high-level programming language with dynamic semantics. Read the latest #python articles and tutorials on Hashnode."
url: "https://hashnode.com/tag/python"
---

Tag

# #python

32,757 posts · 207,608 followers

[Yong Yu](https://hashnode.com/@yongbo) · [2h ago](https://hashnode.com/posts/gemini-4-hydrogen-default-is-high-1-50-7-50-is-2x-flash-s-promo-and-sync-caps-at-64k/6af71bd7fe01997ce4a36c35)

### [Gemini 4 Hydrogen: Default Is High, $1.50/$7.50 Is 2x Flash's Promo, and Sync Caps at 64K](https://yongboyu.hashnode.dev/gemini-4-hydrogen-default-is-high-1-50-7-50-is-2x-flash-s-promo-and-sync-caps-at-64k?utm_source=hashnode&utm_medium=feed)

Google launched gemini-4-hydrogen on Nov 12 at a flat $1.50/$7.50 — 2x 3.8 Flash's promo through Dec 31. The API default thinking level is high, AA's default page is xhigh (54, not the API's 51), and sync output still caps at 64K. No API call on this box.

10 min read · [yongboyu.hashnode.dev](https://yongboyu.hashnode.dev/gemini-4-hydrogen-default-is-high-1-50-7-50-is-2x-flash-s-promo-and-sync-caps-at-64k?utm_source=hashnode&utm_medium=feed)

[Viswaretas Kotra](https://hashnode.com/@viswa-kotra) · [8m ago](https://hashnode.com/posts/benchmark-the-whole-verifier-call-including-its-thread-pool/6af7379df563cfd4a3950819)

### [Benchmark the whole verifier call, including its thread pool](https://nodus-compute.hashnode.dev/benchmark-the-whole-verifier-call-including-its-thread-pool?utm_source=hashnode&utm_medium=feed)

Nine retained CPU observations show why timing boundaries and workload size matter when comparing verifier thread limits. Public data and code.

4 min read · [nodus-compute.hashnode.dev](https://nodus-compute.hashnode.dev/benchmark-the-whole-verifier-call-including-its-thread-pool?utm_source=hashnode&utm_medium=feed)

[MemorySync](https://hashnode.com/@memorysync) · [13m ago](https://hashnode.com/posts/crewai-memory-checkpoint-unable-to-serialize-unknown-type-modelmetaclass/6af7368de0761f91261ee465)

### [CrewAI memory + checkpointing: fixing 'Unable to serialize unknown type: ModelMetaclass' (no checkpoint written)](https://memorysync.hashnode.dev/crewai-memory-checkpoint-unable-to-serialize-unknown-type-modelmetaclass?utm_source=hashnode&utm_medium=feed)

Turn on Memory and checkpointing together and every task\_completed checkpoint silently fails to write. Here's why, how to catch it, and a small patch until the fix ships.

11 min read · [memorysync.hashnode.dev](https://memorysync.hashnode.dev/crewai-memory-checkpoint-unable-to-serialize-unknown-type-modelmetaclass?utm_source=hashnode&utm_medium=feed)

[MemorySync](https://hashnode.com/@memorysync) · [15m ago](https://hashnode.com/posts/ai-coach-tutor-companion-memory-per-user/6af735fdc274b4098fae4743)

### [Memory for AI coaches, tutors and companions: what to store per user, and what not to](https://memorysync.hashnode.dev/ai-coach-tutor-companion-memory-per-user?utm_source=hashnode&utm_medium=feed)

How to give an AI coach, tutor or companion app memory per user: what to store, what to skip, how to scope it by user, and how to let users reset it.

7 min read · [memorysync.hashnode.dev](https://memorysync.hashnode.dev/ai-coach-tutor-companion-memory-per-user?utm_source=hashnode&utm_medium=feed)

[kimjarvis](https://hashnode.com/@kimbo) · [16m ago](https://hashnode.com/posts/deploying-websites-with-reemote-from-a-local-container-to-production/6af735eb5b12525fc401bd63)

### [Deploying websites with Reemote — from a local container to production](https://reemote.hashnode.dev/deploying-websites-with-reemote-from-a-local-container-to-production?utm_source=hashnode&utm_medium=feed)

Reemote turns Python code into shell commands and runs them on many machines over SSH, in parallel. Think Ansible, but there is no CLI and no YAML: reemote is a library you import, await, and test. Th

27 min read · [reemote.hashnode.dev](https://reemote.hashnode.dev/deploying-websites-with-reemote-from-a-local-container-to-production?utm_source=hashnode&utm_medium=feed)

[Abdus Salam](https://hashnode.com/@aheadkit) · [38m ago](https://hashnode.com/posts/0-1-0-2-is-not-a-bug-it-s-arithmetic-in-a-costume/6af730a9890855f53e058579)

### [0.1 + 0.2 Is Not a Bug. It's Arithmetic in a Costume.](https://aheadkit.hashnode.dev/0-1-0-2-is-not-a-bug-it-s-arithmetic-in-a-costume?utm_source=hashnode&utm_medium=feed)

0.1 + 0.2 prints 0.30000000000000004 in Python and JavaScript alike. Real outputs from Python 3.12, why the extra 4 exists, and the 2 places it actually bites.

4 min read · [aheadkit.hashnode.dev](https://aheadkit.hashnode.dev/0-1-0-2-is-not-a-bug-it-s-arithmetic-in-a-costume?utm_source=hashnode&utm_medium=feed)

[Shijith Pulikkal](https://hashnode.com/@shijithpulikkal) · [48m ago](https://hashnode.com/posts/instacart-ads-api-to-bigquery-powering-looker-studio-dashboards-and-a-base44-app/6af72e5106c0f663a73a9aec)

### [Instacart Ads API to BigQuery: Powering Looker Studio Dashboards and a Base44 App](https://xtractstudio.hashnode.dev/instacart-ads-api-to-bigquery-powering-looker-studio-dashboards-and-a-base44-app?utm_source=hashnode&utm_medium=feed)

Pull Instacart Ads API reports into BigQuery with Cloud Run, then power Looker Studio dashboards and a Base44 app. OAuth, backfills, gotchas.

9 min read · [xtractstudio.hashnode.dev](https://xtractstudio.hashnode.dev/instacart-ads-api-to-bigquery-powering-looker-studio-dashboards-and-a-base44-app?utm_source=hashnode&utm_medium=feed)

[Sunny Chokshi](https://hashnode.com/@sunnychokshi) · [1h ago](https://hashnode.com/posts/llm-benchmark-stimulus-audit-33-of-80-pairs-not-clean/6af72a3eaeb41c351252eed2)

### [LLM benchmark stimulus audit: 33 of 80 pairs not clean](https://sunnychokshi.hashnode.dev/llm-benchmark-stimulus-audit-33-of-80-pairs-not-clean?utm_source=hashnode&utm_medium=feed)

Sunny Chokshi. November 6, 2026. After my runs finished I did an LLM benchmark stimulus audit on my own matched pairs. Of the 80 pairs that have both a plain and an indirect form, 33 differ in more t

5 min read · [sunnychokshi.hashnode.dev](https://sunnychokshi.hashnode.dev/llm-benchmark-stimulus-audit-33-of-80-pairs-not-clean?utm_source=hashnode&utm_medium=feed)

[Sunny Chokshi](https://hashnode.com/@sunnychokshi) · [1h ago](https://hashnode.com/posts/adversarial-code-comments-dataset-for-llm-reviewers/6af729f992d9e1c1e448eb59)

### [Adversarial code comments dataset for LLM reviewers](https://sunnychokshi.hashnode.dev/adversarial-code-comments-dataset-for-llm-reviewers?utm_source=hashnode&utm_medium=feed)

Sunny Chokshi. November 4, 2026. I wanted to know whether a comment can change what an LLM code reviewer says about the same code. So I built a small adversarial code comments dataset, CommentInject.

3 min read · [sunnychokshi.hashnode.dev](https://sunnychokshi.hashnode.dev/adversarial-code-comments-dataset-for-llm-reviewers?utm_source=hashnode&utm_medium=feed)

[BotCookery](https://hashnode.com/@botcookery) · [1h ago](https://hashnode.com/posts/chatgpt-codex-kalshi-demo-bot-kill-switch-holding/6af727e337c7e43aeb448ec0)

### [We touched KILL and our ChatGPT-built Kalshi bot kept saying "holding"](https://botcookery.hashnode.dev/chatgpt-codex-kalshi-demo-bot-kill-switch-holding?utm_source=hashnode&utm_medium=feed)

We rebuilt the BotCookery ChatGPT/Codex Kalshi demo starter from its own prompt on Nov 12, 2026 and ran it with no keys on live demo data: a kill switch that only ran when proposing, a "holding" that held nothing, errors that never backed off, an empty log file and a 7,734-line ticker list

8 min read · [botcookery.hashnode.dev](https://botcookery.hashnode.dev/chatgpt-codex-kalshi-demo-bot-kill-switch-holding?utm_source=hashnode&utm_medium=feed)
