Kapwing Reviews

opencode Reviews

Kapwing mentions (25)

• Different Language

  When I visit: kapwing.com, it is showing a different language:https://imgur.com/a/wtBmmU3. Source: over 3 years ago

• I dreamt that songs about sex & sth. weird and unrelated/ odd or impossible sex would be titled “sêx” and even had articles written about them

  Crediting the websites I used for creating this: The first image was made using Tweetgen (the profile pic is a stockphoto); The second one was made using a Fake News Generator -> the picture of the article was made by combining three images created by stable diffusion; The last picture was edited with Kapwing (I took the cover photo myself). Source: over 3 years ago

• No need to thank me, Sony 😎

  To make memes, I just use kapwing.com to put them together. (note: to get rid of the watermark after exporting, just add an extra border to the bottom of the meme, then crop it off after you download it.). Source: almost 4 years ago

• This is a series now

  Anything will do, I used DaVinci Resolve 18, but that is overdoing it. Something like kapwing.com will serve you well. Source: about 4 years ago

• mod cring!!!! (dont mind the watermark I don't know how to crop gif)

  If that doesn’t work, https://kapwing.com also works. Source: about 4 years ago

opencode mentions (67)

• ZCode: Claude Code from the Makers of GLM

  Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 5 days ago

• AI for Less Popular Programming Languages

  OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 7 days ago

• How to Run Reliable Local LLM Agents on an RTX 3090: A Benchmark (5 Models, Priced in Watts)

  I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 8 days ago

• The head chef model of AI collaboration

  Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 17 days ago

• Testing GLM-5.2 on OpenCode: I'm impressed!

  If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 18 days ago