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

331–340 of 346 posts

Re: DeepSeek Harness developer preview

#331

Post by maleldil »

Otterly99 wrote: post #298
moljac024 wrote: post #296

Earlier quoted context omitted.

Can you explain how COT is essential to distillation and why obfuscating it helps defend against distillation? Or point me in the right direction in terms of what to read.

Because they are an integral part of the solution generation. By distilling, you are training a model via Reinforcement Learning (RL) to mimic the answer of a bigger model. To do that, you need all the steps that contributed to generating an answer. To give you a better idea, imagine teaching a student how to solve math problem: 1. You give it the problem and the answer only (no thinking trace) 2. You give it the pro…

Isn't distillation done through SFT by having the student model approximate the teacher's output distribution?

Re: DeepSeek Harness developer preview

#332

Post by Sha1rholder »

mcculley wrote: post #325
Sha1rholder wrote: post #323

Earlier quoted context omitted.

> Aren't there reasons to avoid the scrutiny that might accompany bypassing the Great Firewall? One of the reasons to bypass GFW is to avoid scrutiny. > Doesn't this create a chilling effect? It doesn't. > Or are you claiming that it has zero effect and citizens of China have zero concerns about using websites and speaking freely? Not “zero”, maybe like “0.01”? Better use an anonymous account if you want to criticize…

This has not been my experience working with Chinese citizens. They are mostly very aware that they cannot speak freely.

> They are mostly very aware that they cannot speak freely.

That's correct, and as I said that's one of the reasons Chinese people bypass GFW.

The last paragraph in my previous comment may not have been clear enough. What I meant was that *after bypassing GFW*, you generally have minimal concern, not *before bypassing GFW*

Re: DeepSeek Harness developer preview

#333

Post by mcculley »

Sha1rholder wrote: post #332
mcculley wrote: post #325

Earlier quoted context omitted.

This has not been my experience working with Chinese citizens. They are mostly very aware that they cannot speak freely.

> They are mostly very aware that they cannot speak freely. That's correct, and as I said that's one of the reasons Chinese people bypass GFW. The last paragraph in my previous comment may not have been clear enough. What I meant was that *after bypassing GFW*, you generally have minimal concern, not *before bypassing GFW*

You seem to believe that every potential interlocutor is bypassing the firewall. I know that many are not, because they are afraid of being caught.

Re: DeepSeek Harness developer preview

#334

Post by lukasco »

pyrophane wrote: post #10

I'm curious what peolle are finding with first party vs 3red party harnesses for coding. Do the first party harnesses really have an advantage when paired with the maker's model?

One thing I found was tool calling in GLM 5.2 on github using Claude Code was mostly failing then fixing. But I didn't compare to z.ai's harness. (Nothing to do with Deepseek, sorry.)

Re: DeepSeek Harness developer preview

#336

Post by u8080 »

kaicianflone wrote: post #312
u8080 wrote: post #85

Earlier quoted context omitted.

There is a round icon at the right bottom, where white arc is how much context used - hover for extra info.

Fantastic tq I feel stupid because I’ve seen that for a while now. Do you know more about the autocompaction process? I could use some help there too with ghcp. I don’t see my context going up while abusing smaller context models with long inputs nor do I see a compaction indicator after turns.

GitHub › Copilot › Chat › Summarize Agent Conversation History: Enabled should do the trick I guess

Re: DeepSeek Harness developer preview

#337

Post by culi »

maleldil wrote: post #330
fn-mote wrote: post #309

Earlier quoted context omitted.

Maybe, like sarcasm, this kind of joke would be easier to appreciate if tagged somehow. I think everyone agrees the internet is drowning in AI slop. That makes the joke hard to appreciate on its own.

They were impersonating an AI. You wouldn't complain that a comic started impersonating a celebrity without saying "I'm going to impersonate X now" first.

I don't think that's their point. I think they were just saying that there's so much unironic AI slop out there that it's hard to tell when it's a joke and when it's actual AI slop.

Re: DeepSeek Harness developer preview

#338

Post by JonChesterfield »

youre-wrong3 wrote: post #256
JonChesterfield wrote: post #255

Earlier quoted context omitted.

I really like the json schemas around the tool calls. Much stricter validation than in codex. Git might be worth adding to the top level. Currently you've got LSP, grep, glob nicely structured for non-mutating queries across a codebase, but git is behind bash and that means hope or sandboxing. Thank you for uploading it. Gives a lot of insight into how the deepseek models might expect tool calls to be structured.

I don’t like it. Structures responses really do not work well with LLMs at all. They are one of the biggest causes of issues with tool calling right now.

You prefer having the harness execute any markdown that looks like it might be a tool call? I had a bad time getting that to work reliably whereas a grammar in the sampler gets it right every time.

Re: DeepSeek Harness developer preview

#340

Post by sora2c0314 »

Kuyawa wrote: post #171

I like it, it is beautiful, specially the trajectory tabs, very explicit, detailed on what it does. I like the plugin architecture, I wish they were sorted alphabetically so I don't waste hours looking for a plugin in a sea of unordered text. 9 out of 10 Edit: After creating an app it works as expected, no complains, lots to celebrate, being version 0.1 there is room for more surprises but right now it's the perfect…

[dead]
Post reply on HN