---
title: "#--ai articles | Hashnode"
description: "Explore 39 articles tagged #--ai on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/--ai"
---

Tag

# #\--ai

39 posts · 0 followers

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 24](https://hashnode.com/posts/2026-04-25-openai-super-app-duct-tape-spud/69eb9fa5ba245b8cd0dfd15d)

### [OpenAI's Super App Play: Why Spud + Duct Tape Matter for Builders](https://plzai.hashnode.dev/2026-04-25-openai-super-app-duct-tape-spud?utm_source=hashnode&utm_medium=feed)

Six weeks ago OpenAI tested an anonymous image model on LM Arena under codenames like packingtape-alpha and gaffertape-alpha. Yesterday they shipped GPT-5.5. The word Greg Brockman used on release day was "super app." That framing is not marketing. I...

9 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-25-openai-super-app-duct-tape-spud?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 24](https://hashnode.com/posts/2026-04-24-openai-gpt-5-5-spud/69eac46aad9985759d3b425c)

### [Why OpenAI Shipped GPT-5.5 Just 6 Weeks After 5.4](https://plzai.hashnode.dev/2026-04-24-openai-gpt-5-5-spud?utm_source=hashnode&utm_medium=feed)

Six weeks. That's how long it took OpenAI to ship GPT-5.5 after 5.4. Until this year, frontier labs did that in quarters. GPT-5.5 is OpenAI's latest flagship language model, codenamed Spud, released April 23, 2026 — 6 weeks after GPT-5.4. The name "S...

9 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-24-openai-gpt-5-5-spud?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 23](https://hashnode.com/posts/2026-04-23-ai-github-skills-paradigm/69ea32c30d677e9ef122239d)

### [How a Markdown File Hit 16K Stars: Skills in 2026](https://plzai.hashnode.dev/2026-04-23-ai-github-skills-paradigm?utm_source=hashnode&utm_medium=feed)

A markdown file got 16,500 GitHub stars in less than a week. It contained no code. It was not a library, not a framework, not a CLI. It was a prompt — specifically, a CLAUDE.md file distilling Andrej Karpathy's observations about where LLM coding age...

8 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-23-ai-github-skills-paradigm?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-21-adobe-cx-enterprise-mcp/69e6a145d24136b168bafdb0)

### [Adobe Just Made MCP an Enterprise Procurement Line Item](https://plzai.hashnode.dev/2026-04-21-adobe-cx-enterprise-mcp?utm_source=hashnode&utm_medium=feed)

Seven frontier AI partners named in one press release. Twenty thousand brands running on a platform now built around MCP endpoints. One trillion experiences a year flowing through infrastructure that, until last week, had never used the words "Model ...

8 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-21-adobe-cx-enterprise-mcp?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-18-contextzip-token-savings/69e6491748d42b9870974cbc)

### [66.5% of My Claude Code Tokens Were Wasted. A 200-Line Wrapper Got Them Back.](https://plzai.hashnode.dev/2026-04-18-contextzip-token-savings?utm_source=hashnode&utm_medium=feed)

66.5% of my Claude Code tokens were being spent on output I never needed to read in full. Over 7,172 commands, I watched 37.2M input tokens compress down to 12.5M, which is a number I had to re-check three times before I believed it. The piece of sof...

7 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-18-contextzip-token-savings?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-21-opus-4-7-swe-bench-87-6/69e64cda5614f53eb9c2f48d)

### [Claude Opus 4.7 Hit 87.6% on SWE-bench. The Story Is What It Didn't Charge You.](https://plzai.hashnode.dev/2026-04-21-opus-4-7-swe-bench-87-6?utm_source=hashnode&utm_medium=feed)

Claude Opus 4.7 scored 87.6% on SWE-bench Verified — up from 80.8% on Opus 4.6, a +6.8 point absolute jump announced on April 17, 2026. The sticker price stayed exactly where it was: $5 per million input tokens, $25 per million output. Anthropic ship...

8 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-21-opus-4-7-swe-bench-87-6?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-19-spoonai-ai-newsletter/69e6492124c706ae077351dc)

### [I Built an AI Newsletter for Myself. 11 Subscribers, 49 Posts, Zero Regrets.](https://plzai.hashnode.dev/2026-04-19-spoonai-ai-newsletter?utm_source=hashnode&utm_medium=feed)

Eleven subscribers. Forty-nine bilingual posts. One person pushing the commits. That's the entire accounting sheet of spoonai.me, and I'm telling you those numbers up front because I think they're the most interesting part of the project. TL;DR — I w...

7 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-19-spoonai-ai-newsletter?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-18-hermes-4-training-stack/69e6491dd1454880100955db)

### [DataForge, Atropos, and a 30K-Token Guillotine: Reverse-Engineering Hermes 4's Training Stack](https://plzai.hashnode.dev/2026-04-18-hermes-4-training-stack?utm_source=hashnode&utm_medium=feed)

A 78.4% reduction in overlong outputs — bought at a 4.7–12.7% accuracy hit. That's not a footnote in Nous Research's 94-page Hermes 4 technical report. That's the central tension of their entire post-training philosophy: control costs latency and rel...

9 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-18-hermes-4-training-stack?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 20](https://hashnode.com/posts/2026-04-18-hermes-4-production-checklist/69e6491a48d42b9870974cbe)

### [The Honest Hermes 4 Production Checklist (April 2026 Edition)](https://plzai.hashnode.dev/2026-04-18-hermes-4-production-checklist?utm_source=hashnode&utm_medium=feed)

Four posts, one question that actually matters: should you ship this thing? After three posts pulling apart Hermes 4's benchmarks, tool-calling architecture, and training stack, I've earned an opinion. The 405B is the wrong model for most workloads —...

8 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-18-hermes-4-production-checklist?utm_source=hashnode&utm_medium=feed)

[jidonglab](https://hashnode.com/@jidonglab) · [Apr 18](https://hashnode.com/posts/2026-04-18-hermes-4-tool-calling/69e31f9f6d92bfb6b2da51dc)

### [Hermes 4's Tool-Calling Is Trained as a Separate Skill. Here's Why Your Agent Cares.](https://plzai.hashnode.dev/2026-04-18-hermes-4-tool-calling?utm_source=hashnode&utm_medium=feed)

Nous Research's Atropos RL framework runs ~1,000 task-specific verifiers. Two of those categories are Schema Adherence and Tool Use — not as a shared bucket labeled "function calling," but as separate, explicitly trained behaviors. I wired Hermes 4 4...

7 min read · [plzai.hashnode.dev](https://plzai.hashnode.dev/2026-04-18-hermes-4-tool-calling?utm_source=hashnode&utm_medium=feed)
