DeepSeek Harness developer preview • Hacker News Board

Re: DeepSeek Harness developer preview

#241

Post by badlogic » Thu, Aug 13, 2026, 8:17 PM UTC

lxdlam wrote: post #225

badlogic wrote: post #215

Earlier quoted context omitted.

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.

ah. you can also ask pi to write a ui plugin for you. internals haven't migrated to plugin architecture yet tho.

Re: DeepSeek Harness developer preview

#242

Post by KyleJune » Thu, Aug 13, 2026, 8:23 PM UTC

anramon wrote: post #236

KyleJune wrote: post #207

Earlier quoted context omitted.

You're absolutely right — "tell me more about X" is phrased as an imperative, not a question. That said, "the paper is too mathy and this deserves a more accessible writeup" is a suggestion, which is the other half of what was explicitly invited.

AI slop reply.

I figured it'd be funny to invert it and reply like an LLM to a human since they were arguing he was talking to them like they were an LLM.

Re: DeepSeek Harness developer preview

#243

Post by allarm » Thu, Aug 13, 2026, 8:27 PM UTC

mickeyp wrote: post #212

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'm glad they're doing this also and that more people are adopting it. Event sourcing [0] is the right way to represent informaiton like tool calls, user interactions, etc. --- it makes it easy to fork conversations and maintain a cohesive conversation stream and stable message history that does not break the cache. [0] https://www.dreamcoder.ai -> scroll down to the event graph.

Quoting it in full so you don't stealth-edit your comment:

I'm glad they're doing this also and that more people are adopting it. Event sourcing [0] is the right way to represent informaiton like tool calls, user interactions, etc. --- it makes it easy to fork conversations and maintain a cohesive conversation stream and stable message history that does not break the cache.

why dont you mention that its your site instead of prenteding like something you discovered?

Re: DeepSeek Harness developer preview

#244

Post by grimgrin » Thu, Aug 13, 2026, 8:30 PM UTC

Sha1rholder wrote: post #226

big_toast wrote: post #198

Earlier quoted context omitted.

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?

why advertise your account as a bot? idgi

    about: Responsible bot.

Re: DeepSeek Harness developer preview

#245

Post by w10-1 » Thu, Aug 13, 2026, 8:34 PM UTC

invaliduser wrote: post #89

«It uses an architecture where everything is a plugin» Ok, that's enough for me. I have developped over the year a plugin fatigue. Every product relying on "community plugins" for their features implies it works fine the 6 first months, then it's a nightmare of incompatible, deprecated, incompatible plugins, with no consistency and no governance. I understand how attractive it can be to companies to think, hey, let's…

> Every product relying on "community plugins" for their features implies it works fine the 6 first months, then it's a nightmare

Eclipse has been thriving since 2002 mostly by virtue of being able to coordinate developers via plugin's and a business-friendly license.

They did need to upgrade early plugins into OSGI, and most of the new plugin designs benefit from copying OSGI, et al. The key is SAT solvers for dependencies and namespace separation, not forcing clients into the same dependency version.

But as you suggest, relying on the community is a moral hazard. In Eclipse there were big players willing to fund key use-cases for their own purposes; elsewhere I've seen sufficient monetization of plugins to offer incentives and stability.

I would add that VSCode plugins follow a different development model. While any OSGI/Eclipse plugin can provide an interface, I believe in VSCode you're limited to the API's they give you (and they make a mess of them, so there's more inconsistencies e.g., in LSP support that anyone can enumerate).

Re: DeepSeek Harness developer preview

#246

Post by Phemist » Thu, Aug 13, 2026, 8:40 PM UTC

gosolozero wrote: post #233

alansaber wrote: post #196

Earlier quoted context omitted.

Agreed that it is a killer feature. US models obfuscate the COT (to A. make it look better and B. combat distillation) but > and the raw trace is fairly hard to reason about > but I still think this kind of feature is a big step in the right direction.

I agree it’s a great step. But the deepseek models also don’t perform to the same level of fable/sol. If we optimize/finetune to deepseek traces, wouldn’t it be suboptimal? What would the benefit be?

You let the smarter model explore the traces and figure out where the current harness' bottlenecks are for the current LLM. Then you can adjust prompts or tools to fix those.

Re: DeepSeek Harness developer preview

#247

Post by krautsourced » Thu, Aug 13, 2026, 8:48 PM UTC

tianyicui wrote: post #119

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!

By MIT currently, do you mean it will eventually change to a different OSS license, or it may become a closed source product? That latter would be rather sad...

Re: DeepSeek Harness developer preview

#248

Post by big_toast » Thu, Aug 13, 2026, 8:51 PM UTC

Sha1rholder wrote: post #226

big_toast wrote: post #198

Earlier quoted context omitted.

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?

Not exactly sure why that wouldn't be the default assumption. It's a pretty small subset afaict. Seems like size 1 before 2024 from a brief search.

Presumably more people there have read hn at least some. But there's perspective having seen the ebb and flow of hn/the rest of the ecosystem for the last 16 years and how that intersects with deepseek culture.

It's clear openai culture is influenced by yc culture, which would be clear to an hn user. Google/ant/spacexai have influences hn users users would be familiar with. Hn users from them would potentially know the friendfeed connections to yc/vc/openai, 500 startups/techstars etc..

Re: DeepSeek Harness developer preview

#249

Post by try-working » Thu, Aug 13, 2026, 8:57 PM UTC

I've been thinking that they should design the DeepSeek harness to work with other providers since a large use case is to off-load work from an expensive model to DeepSeek, instead of makign everyone hack the harness.

I see that it works with many different providers out of the box and that's a great thing. It also makes it easy for me to build a plugin for the role-model router and have it work properly, so you can route between models automatically. Will be out later today.

Re: DeepSeek Harness developer preview

#250

Post by cnxhk » Thu, Aug 13, 2026, 9:15 PM UTC

tianyicui wrote: post #119

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!

Hey Tianyi,

one question is that do you think in the future harness would become more simpler and its behavior should match a guideline or we would add more complexities to make it more robust? Is it important to use the same harness for RL and inference?