| ▲ | micw a day ago |
| My strategy: diversification. I run deepseek harness (which I made a vs code integration for and extended it a lot with plugins) and integrated it with my codex and claude subscriptions as well as an openrouter account. This way I can switch models and providers during my sessions and does not get blocked on such things. Useful for
- outages
- running out of quota
- failing agents e.g. because of "cyber" flaging |
|
| ▲ | mark_l_watson a day ago | parent | next [-] |
| Good diversification. I like to have a strong local model like qwen3.8-flash-next available because I live in the mountains and my Internet is not 100% reliable. I don’t get it that companies allow themselves to get locked in on one vendor. Two or more, with local makes more sense. |
| |
| ▲ | qrux a day ago | parent [-] | | You're on HN, and "vendor lock-in" surprises you? ;) |
|
|
| ▲ | Doohickey-d a day ago | parent | prev | next [-] |
| How long has this been working for you? (Or others). Since Anthropic doesn't seem to like subscriptions being used in third party harness, do they actually enforce that nowadays? |
| |
| ▲ | micw a day ago | parent [-] | | https://github.com/micw/claude-wrapper-advanced
I wrap their CLI ^^ Edit: CLI in headless mode is an official feature | | |
| ▲ | Doohickey-d 21 hours ago | parent [-] | | Okay, this is slightly horrifying to me but also a bit genius... But I guess Anthropic models are trained for Claude Code's tool call shape (i.e. the edit tool). Does it deal well enough with the MCP tools that Deepseek harness gives the model instead? | | |
| ▲ | micw 18 hours ago | parent | next [-] | | I don't think that "Anthropic models are trained for Claude Code's tool call shape". It's all about system prompt and model description (which is part of that prompt). I observe that most models can deal well with the tools you provide. Form time to time I analyze my sessions to see which tools could improve my (or my agent's) work. E.g. a background timer/watcher is on my todo list, so that I can chat with the agent session while its waiting for some shell response. | |
| ▲ | antonvs 12 hours ago | parent | prev [-] | | > Okay, this is slightly horrifying to me but also a bit genius... If you're old enough to remember CGI web services, originally every request to a web server for non-static content launched a binary. Most of the web ran on that approach for a long time, later optimized with things like FCGI. |
|
|
|
|
| ▲ | Bender a day ago | parent | prev | next [-] |
| dsh looks intriguing. Do they have any plugins that help effectively extend the context memory of each of the LLM's? I am starting to watch some videos on it but it will take me a while to get through them. |
| |
| ▲ | micw 18 hours ago | parent [-] | | I think there are plenty ways to "extend the context memory". Compaction is the most obvious: reduce old context to it's core and free tokens. Another tool is session search. The models can look back in parts of the session that got "compacted away" and also in other sessions. But honestly with 500k or 1m token sessions, I rarely run out of context memory and barely notice any loss of precision after compaction. |
|
|
| ▲ | djc404 14 hours ago | parent | prev | next [-] |
| Can OpenCode work in the same way? |
|
| ▲ | thefourthchime a day ago | parent | prev [-] |
| For coding, I wouldn't use deepseek as a replacement. At least not for anything hard. |
| |
