Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek Harness developer preview

deepseek.com

Post reply on HN
Print view View original

111–120 of 346 posts

Re: DeepSeek Harness developer preview

#111

Post by tosh »

syntaxing wrote: post #5

Is there a reason why so many of these agent harness are written in node.js?

codex is written in rust fwiw

smol has implementations in Go, Python, Clojure, PHP

https://github.com/smol-env/smol

out of the box an agent only needs to be able to do http requests and call tools (which might again be just http requests or shelling out)

there is no inherent reason for why an agent has to be in JavaScript or Typescript

but they are popular languages and come with runtimes and libraries for http requests, steaming, TUI (terminal ui) and so on which can help

Re: DeepSeek Harness developer preview

#112

Post by JSR_FDED »

bpodgursky wrote: post #81
rco8786 wrote: post #17

But like, what is it? Odd that this reached #1 on HN. The README is pretty bare outside of installation instructions and a link to "Cordis", which is "A Meta-Framework of Spatiotemporal Composability." and "under active development. The API is not yet stable and may change without notice.".

[flagged]

You don’t think it’s because titanic battles are interesting and here’s a company that (a) gives you the weights to a frontier model for free, (b) publishes great papers with LLM architecture innovations, (c) is insanely cheap?

Re: DeepSeek Harness developer preview

#113

Post by scotty79 »

grommz wrote: post #108
lxdlam wrote: post #58

I 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.

It's modular by default so you can experiment freely, in-session. If you don't like some plugin you built, just disable it and move on. No need for tracking changes, reverting and so on if you keep your plugins focused.

Re: DeepSeek Harness developer preview

#115

Post by hmokiguess »

wongarsu wrote: post #86
hmokiguess wrote: post #47

Tangential but, are there benchmarks out there on how languages affect latent spaces and performance of these models? This other day I was looking at that “caveman” skill, and was shocked to see it evolved to become a company, and, in one of its modes, the highest form of compression seems to be “Wenyan” which is Classical Chinese. Should I get started on learning Chinese?

There are lots of papers on the topic. I think the best summary is "it's complicated". Typically models perform slightly better in English, typically best in either professional English or very rude English. Though this varies by model, not all react well to rude English, and I wouldn't be surprised if Chinese was on the rise Also, "less tokens" is not always straight forward. I doubt it's a coincidence that the cave…

Very interesting, can you link some of the papers if you don't mind? I'm curious about this space.

I'm finding more and more there seem to be sort of niche prompting skills that are important to be aware of

Re: DeepSeek Harness developer preview

#117

Post by scotty79 »

rco8786 wrote: post #93
kamranjon wrote: post #33

Earlier quoted context omitted.

New coding harness that seems to have some novel concepts and one of the pretty cool things on their landing page for it here: https://deepseek.com/harness/en/ is the Every Run is Traceable view: "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…

I promise this isn't meant to be snarky, but is that not just...logs?

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.

Re: DeepSeek Harness developer preview

#118

Post by lalitmaganti »

lxdlam wrote: post #58

I 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…

This is basically similar to what bb (https://getbb.app/) is also doing. It's interesting to see many different people exploring things in this space...

Re: DeepSeek Harness developer preview

#119

Post by tianyicui »

Hi 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!

Re: DeepSeek Harness developer preview

#120

Post by schafberg »

flaburgan wrote: post #73

Is there a comparison of harness somewhere? Like, the same prompt to the same model, but with different harnesses, and comparing the quality of the results. I am trying to run as much as possible only on free software, so I always only used Zed plugged with anthropic models, but I am wondering what is the quality of Zed harness compared to the one of claude code or pi or others... I would love some feedback.

I want to have the same thing, but tbh it's too complicated with so many configuratios and plugins. I doubt if any comparison of harness make sense now and can be applied in real coding works.
Post reply on HN