opencode Reviews

TestGorilla Reviews

1. AnnaBenjamin

   6 months ago
   Solid Skill Testing Platform — Good, but Not Perfect for Every Hiring Need

   We’ve been using TestGorilla as part of our hiring process to screen applicants before bringing them into interviews, and it’s proven quite useful. The idea is simple but helpful: instead of spending hours reviewing resumes, you give candidates a relevant test right away. Seeing how people perform on real job-related tasks gives us a much clearer picture early on.

   The test library is broad, covering everything from coding challenges and software proficiency to logical thinking and communication skills. Setting up and sending tests doesn’t take long, and the results are laid out in a clear way that makes comparison between applicants straightforward.

   Where it falls a bit short is in the depth of some tests — a few feel like they’re too surface-level to really separate top performers from average ones. Creating your own custom assessments is possible, but the interface for doing that could use refinement. Also, once you scale up hiring, costs add up — especially if every team needs access.

   Overall, TestGorilla adds real value to the recruiting process by helping weed out unfit candidates early and giving objective data on skills — which is why I give it 4 out of 5 stars.

   👍 Pros:    Clean dashboard makes it easier for hiring teams to review re

   👎 Cons:    Custom test creation could be more intuitive

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 / 20 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 / 23 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 / 24 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 / about 1 month 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 / about 1 month ago

TestGorilla mentions (1)

• Need advice on hiring process for dev team

  What I had in mind was using either SHL-style aptitude tests, or third party assessments like testgorilla.com rather than a take-home exercise that I'd be moderating. I also remembered doing an online knowledge test of various web technologies when I used to be a web-dev - which could be useful for assessing Unity/C# knowledge. Source: almost 4 years ago