Is there a reason why so many of these agent harness are written in node.js?
I'm still waiting to find one written in Rust that I really love. I don't think js/ts makes sense for terminal based applications
DeepSeek Harness developer preview
291–300 of 346 posts
Re: DeepSeek Harness developer preview
#292There 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…
Every company gets a limited number of innovation tokens. Where they choose to spend them is up to them. Some companies spend them on the model harness, some, like DS, spend them on the model architecture etc. https://mcfunley.com/choose-boring-technology
When it's a fast moving field that alleges to produce "AGI" and there are 8 near-identical options I'd argue it merits more innovation tokens
Re: DeepSeek Harness developer preview
#293I'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?
I feel very strongly the first party harnesses don't make sense when essentially every month the Pareto frontier changes as new models get released
I want to use the same consistent working surface across models in the same way I want to use the same text editor across all different languages
Re: DeepSeek Harness developer preview
#294Hi 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!
The best kept secret in AI training. Tianyi, since you are our insider. When you walk by the training teams office - how often do you see Pelicans on their screens?
Re: DeepSeek Harness developer preview
#295Hi 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...
Sorry for the confusion. I'm not a native English speaker. What I meant is "currently in developer preview".
Re: DeepSeek Harness developer preview
#296"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…
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.
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.
Re: DeepSeek Harness developer preview
#297Hi 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)?
> Anything you think hn doesn't know about deepseek that it should?
We do hire people who are currently located outside of China (say North America, Europe, or anywhere) if they're open to work in our Beijing or Hangzhou offices.
Re: DeepSeek Harness developer preview
#298Earlier 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.
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 problem, the intermediary steps and the answer (full transcript)
I think you can agree that the second method is more likely to give a well-informed student.
Re: DeepSeek Harness developer preview
#299Earlier quoted context omitted.
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…
It *is* a small subset, but I don’t see what’s so surprising. HN is just an ordinary tech community; it’s not surprising for people from any tech company to show up there.
But... no-one mentioned surprise except you, did they? Something being uncommon doesn't connote being surprising, at least not always.
It's uncommon for me to have takeaway pizza, but I don't think anyone I know would be surprised when I do.
Re: DeepSeek Harness developer preview
#30047mb downloaded, 1.5gb after build, wtf? I consider my own coding agent bloated at just 1mb (yes 1mb) because it uses postgresql package as db tool, and it works wonders. * edit 1: Upon further scrutiny, 35 dependencies make up for 1.4gb, what they are for? I don't even see postgres in there so I guess that would be another plugin. 1.5gb of basic functionality? * edit 2: Most of the time I use the terminal but also d…
NODE_MODULES