ChatGPT Reviews

1. MeganMills

   6 months ago
   The Future

   ChatGPT is a friendly and powerful AI assistant that understands questions and gives clear, helpful answers almost instantly. It feels like talking to a knowledgeable and patient expert whether you need help with writing, learning new topics, solving problems, or even just brainstorming ideas. While it’s not perfect and sometimes can misinterpret tricky prompts, overall it’s impressive, easy to use, and surprisingly human-like in conversation. A great tool for students, professionals, and curious minds alike

   👍 Pros:    Quick response time

   👎 Cons:    Critical thinking
2. Sakasa

   about 1 year ago
   my personal assistant at work

   I recently acquired access to ChatGPT, one of the most advanced language models out there, and I must say it has made a significant impact on my analytics work. It has definitely become an integral part of my daily use.

   Analytical support: ChatGPT does a great job of providing accurate and timely answers. It can also help me analyze large amounts of data. Efficiency: This product allows me to work more efficiently by using it to quickly find information or get recommendations.

3. Word.Studio

   · Editor at Word.Studio · over 1 year ago
   The essential AI everything tool.

   OpenAI continues to lead the way among the foundation model providers. I started using ChatGPT at 3.5 much like many other people. And although it was extremely powerful, it doesn't compare to what it has become with the new reasoning models like o1 and o3. These models produce outputs that are on a new level in terms of quality.

   I've been using custom GPT's extensively and they are very valuable once you get them dialed in to your own specific workflows. they recently rolled out projects which also have the ability to add custom instructions. Many of the custom GPT's that I've made do not need anything other than custom instructions. They don't need Web hooks or documents to reference, so a project will suffice. projects also allow connecting and switching between some of the newer reasoning models as well while custom GPT's are limited to the 4o model.

   Real time voice assistant is a game changer when you are on the go. And the human-like speech synthesis is incredible. uploading photos and giving the voice assistant access to live video from your phone has so many use cases that I have yet to realize.

   Many of the tools we have on WordStudio are powered by the OpenAI family of models via API. We recently hooked some of the tools to their o1 model and the improvements in the outputs are astounding.

   I've tried Anthropic's Claude and have experimented with DeepSeek, but I keep returning to ChatGPT for critical work.

   🏁 Competitors: Claude by Anthropic, Deepseek R1, Llama

   👍 Pros:    Active development|Powerful models|Api & webhooks|Multi modal|Canvas mode for long-form content and code|Text, image + video generator

   👎 Cons:    Image generator is lacking|Organization of chats is cumbersome

Pi Coding Agent Reviews

ChatGPT mentions (845)

• Claude's Paid Subscribers Are Skyrocketing

  Anthropic ran Super Bowl ads that directly targeted OpenAI. The message: ChatGPT is showing you ads. Claude never will. - Source: dev.to / 3 months ago

• How to Intercept Server-Sent Events in Chrome Extensions (MV3 Guide)

  { "manifest_version": 3, "name": "SSE Interceptor", "version": "1.0", "permissions": ["activeTab", "storage"], "content_scripts": [ { "matches": ["https://chat.openai.com/*", "https://chatgpt.com/*"], "js": ["content-isolated.js"], "run_at": "document_start" }, { "matches": ["https://chat.openai.com/*", "https://chatgpt.com/*"], "js": ["content-main.js"], ... - Source: dev.to / 4 months ago

• How I Built an AI Suggestion Textbox with Angular Signal Forms

  AI suggestion textboxes are everywhere right now. From GitHub Copilot to ChatGPT, folks expect AI assistance when working with forms. Adding this capability to your forms doesn't have to be complicated. By creating a custom form control with Angular Signal Forms, you can integrate AI-powered suggestions seamlessly while maintaining proper form state management, request cancellation, and error handling. This... - Source: dev.to / 6 months ago

• Ask HN: What Are You Working On? (January 2026)

  Top of my ideas now: add "ask your LLM" buttons to my newsletter card that opens ChatGPT/Perp/Claude and auto-fills a query. Sample links: Claude: https://claude.ai/new?q=Do+deep+research+on+a+person%2C+dvsj.in+and+tell+me+succinctly+why+I+should+be+friends+with+him. ChatGPT: https://chat.openai.com/?q=Do+deep+research+on+a+person%2C+dvsj.in+and+tell+me+succinctly+why+I+should+be+friends+with+him. Also working on... - Source: Hacker News / 6 months ago

• 🧩 Runtime Snapshots #11 — The Design Loop: From 'Make It Like That Site' to Pixel-Perfect Code

  Drop an image into Claude or ChatGPT asking it to "recreate this." The result? The LLM guesses styles. Is that padding 16px or 24px? Is that blue #3b82f6 or #2563eb? Is the shadow 0 2px 8px or 0 4px 12px? Pure hallucination. - Source: dev.to / 6 months ago

Pi Coding Agent mentions (11)

• How I Manage My VPS With Pi’s SSH Extension

  Pi is a minimal, open-source agentic harness: a terminal program that wraps a language model with the tools it needs to read files, edit code, and run shell commands similar to any existing AI terminal like Claude Code or OpenCode. The difference is that SSH extension routes those shell commands to a remote server instead of your local machine, so you can administer a VPS in plain language while reviewing each... - Source: dev.to / about 10 hours ago

• Ask HN: Is anyone experimenting with different ways of using LLMs for coding?

  Thanks to being unemployed, the last few months I've been experimenting a lot with coding agents, harnesses and most importantly, the workflows around them. Currently I'm refining what I think works best for me, which I'd call something like "issues/PR based LLM workflow", powered mainly by this action I'm building on top of the [Pi coding agent](https://pi.dev) SDK:... - Source: Hacker News / 4 days ago

• ZCode: Claude Code from the Makers of GLM

  If you haven't yet you should give a chance to https://pi.dev I've been using it exclusively (and extending it, see https://a.l3x.in/ai) for months with mainly GLM-4.7 then 5.1 and now 5.2 and I could hardly be any happier. I'm still working on a "Github/Forgejo first" based workflow but also quite happy with it already, basically most of my sessions run as a ci/cd job (triggered by "/pi" comments) and generate... - Source: Hacker News / 6 days ago

• Ask HN: Line by Line Agentic Coding

  I like to use Pi (https://pi.dev/), and I recently got it to make an approval extension for itself. It has a lot of documentation built-in for the agent to modify the behavior of the app. I got it to display all proposed file change diffs and bash commands and made it so I can either approve the action or deny it with a message for it. It was surprisingly easy to tell it to modify things things the diff viewing... - Source: Hacker News / 6 days ago

• Claude Code Is Steganographically Marking Requests

  For open source agents, like https://pi.dev, it is as easy as asking it to create a plugin to stop the session or ask for permission whenever the LLM is trying to execute a commit command. Then you add one line in AGENTS.md stating the LLM should never commit, push or perform any write git operation without explicit being asked to. So in the very rare case that the LLM bypass you instruction, you catch it... - Source: Hacker News / 7 days ago