Based on our record, Codex by OpenAI should be more popular than Gotty. It has been mentiond 73 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
I use nix-on-droid to keep a dev environment on my phone. Sometimes I have an hour or two to kill in the university library. I use their computers' screens and keyboards, but I'm coding on my phone through a browser tab and https://github.com/yudai/gotty Beats the hell out of trying to be productive on Windows. - Source: Hacker News / about 1 year ago
The shell itself doesn't really seem any better than e.g. [gotty](https://github.com/yudai/gotty), and there's a bunch more similar things, so at the moment, doesn't seem too useful... - Source: Hacker News / about 1 year ago
(FYI: A fun manual remote terminal. Totally insecure, but fun.). Source: about 2 years ago
Thank you for all the suggestions. I tried some of these and decided to go with GoTTY: Https://github.com/yudai/gotty. Source: about 2 years ago
I love the command line and I am not fan of HTML. I recently learned about web terminals ( gotty ), got excited and I thought to myself: couldn't it be a new (old!) paradigm for web apps? This would be especially useful for back office, administration tasks. Source: over 2 years ago
> incorrect, its an o3 finetune. This is Open AI's fault (and literally every AI company is guilty of the same horrid naming schemes). Codex was an old model based on GPT-3, but then they reused the same name for both their Codex CLI and this Codex tool... I mean, just look at the updates to their own blog post, I can see why people are confused. https://openai.com/index/openai-codex/. - Source: Hacker News / 25 days ago
The big step function here seems to be RL on tool calling. Claude 3.7/3.5 are the only models that seem to be able to handle "pure agent" usecases well (agent in a loop, not in an agentic workflow scaffold[0]). OpenAI has made a bet on reasoning models as the core to a purely agentic loop, but it hasn't worked particularly well yet (in my own tests, though folks have hacked a Claude Code workaround[1]). o3-mini... - Source: Hacker News / about 2 months ago
Fine-tuning based learning (pre-trained optimization). For example, a language model (e.g., OpenAI Codex) fine-tuned for the software development tasks. - Source: dev.to / 5 months ago
> there's no CodeGPT, its just GPT4 Codex[1] is OpenAI's CodeGPT. It's what powers GitHub Copilot and it is very good but not publicly accessible. Maybe they don't want something else to outcompete Copilot. [1] https://openai.com/index/openai-codex/. - Source: Hacker News / about 1 year ago
> it would need some human touch but most of the work will be done already By that very loose standard, the matter of time is 2 years 6 months 18 days ago — August 10, 2021 was OpenAI's blog post about the Codex model, with a chat interface producing functional JavaScript: https://openai.com/blog/openai-codex Right now, what I see coming out of these tools (and what I see in the jobs market) gives me the... - Source: Hacker News / over 1 year ago
Teleconsole - Teleconsole is a free service to share your terminal session with people you trust.
GitHub Copilot - Your AI pair programmer. With GitHub Copilot, get suggestions for whole lines or entire functions right inside your editor.
Pagekite - Bring your localhost servers on-line.
Tabnine - TabNine is the all-language autocompleter. We use deep learning to help you write code faster.
Warp - Warp (Windows Advanced Rasterization Platform) is a high-speed software rasterizer tool designed for the accurate reproduction of bitmap graphics on modern microprocessor-based systems.
Kite - Kite helps you write code faster by bringing the web's programming knowledge into your editor.