Earlier quoted context omitted.
Logs that aren't missing anything out of the box. I'd say it's pretty underused concept in time of 8TB consumer SSD drives.
Don't those cost 1-2k?
Closer to 1k, even pcie 5 versions.
DeepSeek Harness developer preview
221–230 of 346 posts
Re: DeepSeek Harness developer preview
#222In the age of LLMs, if your new hires are pushing npm slop, with all the cargo culting and security pwn issues it brings, your hiring process has failed you oof
What if the old hires are doing it?
Re: DeepSeek Harness developer preview
#223"Every run is traceable Everything the model sees is recorded in an append-only session log: system prompts, reasoning, tool calls and results, subagent scheduling, and every context injection. In the Trajectory view, you can inspect these records by source. Resume, fork, search, and replay all operate on the same event stream." That's a killer feature, IMHO, and one that US models won't allow you to do, as their tra…
I get that today through Tailscale Aperture as an AI Gateway though, highly recommend!
Re: DeepSeek Harness developer preview
#224I have read the underlying paper, and found it may be useful, but not that useful. For those who want to know what it achieves: it adds hot-reload and dynamic enable/dispose capabilities to a plugin system, like the one in Pi agents, though they push the boundaries further, to the UI components and so on. For those who want to know what it does: if you have some PLT knowledge, ask your agent to explain the algebra to…
The paper mentions agent harness self improvement as one of the use cases. I don't know what's the advantage vs. iterating over a monolithic harness.
I have some self-improving harness tooling, I run it within Claude Code because of the cost advantage but that does mean restarting Claude Code periodically so it can pick up all changes. It sounds like the DeepSeek system won't need that, which is useful.
Re: DeepSeek Harness developer preview
#225I have read the underlying paper, and found it may be useful, but not that useful. For those who want to know what it achieves: it adds hot-reload and dynamic enable/dispose capabilities to a plugin system, like the one in Pi agents, though they push the boundaries further, to the UI components and so on. For those who want to know what it does: if you have some PLT knowledge, ask your agent to explain the algebra to…
just read the paper, and there aee definitely some interesting ideas in it. a plugin's registrations returning individual cleanup handlers is nice. in pi, you clean up all registrations in one go in the session-shutdown handler. i also like the use of generator to to clean up partial registrations nicely. the cross-plugin dependency injection and resolution i'm not so sure about. it comes with a lot of footguns and l…
If you run the `dsh`, you can go to the Settings -> Plugins, and you can find that they just write all UI components as plugins(maybe not all, I don't check). Also, you may ask the harness to write a UI plugin for you, I just read some neat examples somewhere.
Re: DeepSeek Harness developer preview
#226Hi I'm one of the authors of DeepSeek Harness. It's just an early developer preview version we're presenting in MIT license currently. Expect lots of rough edges and compatibility-breaking changes. Any feedback and suggestions are more than welcome!
Sorry for the off topic question. You've been on hn a long time + work at deepseek which seems pretty uncommon. Anything you think hn doesn't know about deepseek that it should? Or any non-obvious ways hn/yc has influenced deepseek (or the broader ecosystem)?
Sorry for the off topic question. Why is "being on hn a long time + working at deepseek" "seems pretty uncommon" to you?
Re: DeepSeek Harness developer preview
#227Is there a reason why so many of these agent harness are written in node.js?
TypeScript's type system is extremely expressive while still allowing you to retain the flexibility of a scripting language. v8 and JSC also have decades of performance tuning across basically every consumer device.
Re: DeepSeek Harness developer preview
#228There is such a clear lack of innovation drive in this field. Every lab just copies what the other does. One of the most baffling things to me is how the once-upon-a-time good developer instinct to make everything reusable, testable, and deterministic is just getting lost into a sea of markdown begging a language model to please act a certain way. For example this repository has a "skill" definition that consists in…
First, cloning a repo doesn't bring the hooks with it - so it's not just as simple as saying "use git hooks". Second, if the repo had hooks and instructions for the LLM or user to blindly install/enable the hooks, we'd instead be complaining about security risks and what might happen if the repo is compromised at some point in the future. Third, sometimes you don't want to mechanically enforce things via git hooks be…
First, I'm SURE there are ways to send scripts from one computer to another over the internet.
Second, the point isn't about a specific repo, it's the general tendency to rely on fuzzy .md files scattered all over the place. And I really don't see how letting the output of a language model run a one time command is more secure than running a script.
Third, "nothing applies in all context"? Yeah, obviously. And harness hooks (at least with Claude code) are still more suggestions than anything else. The only way I've found is literally rejecting a tool use and forcing it to recall in the proper way, which of course makes for more token usage. I wonder who benefits from that.
Finally, no idea what you are arguing against. Use git hooks where they make sense, local or remote.
Re: DeepSeek Harness developer preview
#229Everything is a plugin? I'm reminded of Eclipse!
Re: DeepSeek Harness developer preview
#230I was working on same idea but left in between and thank god they did it. Why I left that idea is because as a developer I know that was needed but I have limited time so I need to build that is really next path forward. I am working on whole dev space that can run on my Mac M4 or similar specs. I needed to revamp everything (LLM thinking) from ground up even models. My idea is mixing deterministic nature of existing…
> My idea is mixing deterministic nature of existing tooling (non-LLM tooling) with non-deterministic nature of LLMs.
This is the fundamental idea behind every LLM harness.