> The market for "coding harnesses" and "AI IDEs" is already oversaturated and they are effectively a commodity at this point, you can use any of them with any provider more or less interchangeably.
Yes and no. I've used a few different harnesses with closed and open models and there is definitely something going on that makes some harnesses work better than others. Many of the differences are hard to pin down and some are things people don't care about. But I wouldn't say they are commodified just yet.
1. Memory use. I have colleagues complaining that Clause Code uses several GB of memory. Meanwhile I haven't heard about that regarding codex or goose, or even opencode for that matter.
2. Suitability for local models. When you use Anthropic models, you use Anthropic as a provider. They can have software between the model and your harness that will fix issues with the model. One notable thing that even the best open weights models struggle with is broken tool calls. There is a lot that a harness can do to fix broken tool calls when working with a straight up ollama running a raw GGUF file.
3. Ease of use with non mainstream models. OpenCode has GREAT coverage of models/providers. Goose, less so as it relies on people to set up their own anthropic or openai compatability settings. e.g. Zed doesn't let you use Z.ai (which, if you speak British English, sounds ironic because "zed ai" isn't directly supported by Zed the editor).
4. Worktree support. Opencode and probably all the TUI harnesses works in a local directory - so you need the terminal to be in the worktree. Zed, however, works centrally on your git repo and tracks the worktrees so you can bounce around your work in a single window.
Of these, '2' is maybe the most important one but also the hardest to pin down as a feature. '3' is a one time cost. Of course '1' could be a blocker for someone using a macbook air or neo.
Because they are based on [the west coast of the US](https://en.wikipedia.org/wiki/American_frontier). DeepSeek, Z.ai, Moonhsot, and Mistral are never called frontier because they aren't based in California.
I don't mind the AI features per se, but is there a configuration setting to sent the traffic through a local AI Gateway to prevent the AI from receiving private information? At the very least to track what is sent over the wire.
On thing that troubles me is that code reviews are also an educational moment for seniors teaching juniors as well as an opportunity for people who know a system to point out otherwise undocumented constraints of the system. If people slack on reviews with the agent it means these other externalities suffer.
Are being handling this at all? Is it no longer needed because it gets rolled into AGENTS.md?
> the AA-Omniscience Hallucination Rate Benchmark which puts 3.0 Pro among the higher hallucinating models. 3.1 seems to be a noticeable improvement though.
As sibling comment says, AA-Omniscience Hallucination Rate Benchmark puts Gemini 3.0 as the best performing aside from Gemini 3.1 preview.
> Stop citing single studies as definitive. They are not. Check if the ones you are reading or citing have been replicated.
And from the comments:
> From my experience in social science, including some experience in managment studies specifically, researchers regularly belief things – and will even give policy advice based on those beliefs – that have not even been seriously tested, or have straight up been refuted.
Sometimes people use fewer than one non replicatable studies. They invent studies and use that! An example is the "Harvard Goal Study" that is often trotted out at self-review time at companies. The supposed study suggests that people who write down their goals are more likely to achieve them than people who do not. However, Harvard itself cannot find such a study existing:
[1]: https://www.documentcloud.org/documents/26073615-c-2025-5430...