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

Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

tongyi-agent.github.io

Post reply on HN
Print view View original

121–130 of 156 posts

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#121

Post by remus »

tbruckner wrote: post #34

Has anyone found these deep research tools useful? In my experience, they generate really bland reports don't go much further than summarization of what a search engine would return.

I run a small website and am based in the UK and have used it a couple of times to summarise what I need to do to comply with different bits of legislation e.g. Online Safety Act. What's really useful for me is that I can feed in a load of context about what the site does and get a response that's very tailored to what's relevant for me, and generate template paperwork that I can then fill out to improve my position with regard to the legislation.

For sure it's probably missing stuff that a well payed lawyer would catch, but for a project with zero budget it's a massive step up over spending hours reading through search results and trying to cobble something together myself.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#122

Post by semi-extrinsic »

fragmede wrote: post #90
criemen wrote: post #80

Earlier quoted context omitted.

> or if it takes a couple of months to fold these advantages back into the frontier models. Right now, I believe we're seeing that the big general-purpose models outperform approximately everything else. Special-purpose models (essentially: fine tunes) of smaller models make sense when you want to solve a specific task at lower cost/lower latency, and you transfer some/most of the abilities in that domain from a bigg…

Right, the Costco problem. A small boutique eg wine store might be able to do better for picking a very specific wine for a specific occasion, but Costco is just so much bigger that they can make it up in Volume and buy cases and cases of everything with a lower markup, so it ends up being cheaper to shop at Costco, no matter how much you want to support the local wine boutique.

In Norway there is a state-owned monopoly on selling wine and liquor (anything above 4.75% ABV). They have 350+ physical shops, a large online shop and around $2bn annual revenue. This makes them one of the largest purchasers of wine and spirits in Europe, and they can get some very good deals.

So even though you have high taxes and a restrictive alcohol policy, the end result is shops that have high customer satisfaction because they have very competent staff, excellent selection and a surprisingly good price for quality products.

The downsides are the limited opening hours and the absence of cheap low-quality wine - the tax disproportionally impacts the low quality stuff, almost nobody will buy shitty wine at $7 per bottle when the decent stuff costs $10, so the shitty wine just doesn't get imported. But for most of the population these are minor drawbacks.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#123

Post by enraged_camel »

barrell wrote: post #108
criemen wrote: post #80

Earlier quoted context omitted.

> or if it takes a couple of months to fold these advantages back into the frontier models. Right now, I believe we're seeing that the big general-purpose models outperform approximately everything else. Special-purpose models (essentially: fine tunes) of smaller models make sense when you want to solve a specific task at lower cost/lower latency, and you transfer some/most of the abilities in that domain from a bigg…

> If/when frontier model development speed slows down You do not believe that this has already started? It seems to me that we’re well into a massive slowdown

Not the OP but I use AI all day every day and have noticed substantial improvements in the models over the past ~6 months. GPT-5 was a huge leap (contrary to reporting) and so was Sonnet 4.5.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#125

Post by ukuina »

kmarc wrote: post #73
ainch wrote: post #63

Earlier quoted context omitted.

The reports are definitely bland, but I find them very helpful for discovering sources. For example, if I'm trying to ask an academic question like "has X been done before," sending something to scour the internet and find me examples to dig into is really helpful - especially since LLMs have some base knowledge which can help with finding the right search terms. It's not doing all the thinking, but those kind of bro…

I caught myself that most of my LLM usage is like this: ask a loaded, "filter question" I more or less know the answer for, and mostly skip the prose and get to the links to its sources.

The "loaded question" approach works for getting MUCH better pro/con lists, too, in general, across all LLMs.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#126

Post by ukuina »

oofbey wrote: post #104
VladVladikoff wrote: post #96

Recently I gave a list of 300 links to deep research and asked it to go through each one to analyze a certain question about them. Repeatedly it would take shortcuts and not actually do the full list. Is this caused by a context window limits? Or maybe Open AI limits request size? Is it possible to not run into these types of limits with locally hosted models?

I’ve also had extremely poor luck getting any LLM agent to go through a long list of repetitive tasks. Don’t know why. I’d guess it’s because they’re trained for transactional responses, and thus are horrible at repute anything.

Very much this.

You are better off asking it a write a script to invoke itself N times across the task list.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#127

Post by andai »

tbruckner wrote: post #34

Has anyone found these deep research tools useful? In my experience, they generate really bland reports don't go much further than summarization of what a search engine would return.

You can copy-paste it into your favorite LLM and ask questions about it. That solves several problems simultaneously.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#128

Post by andai »

blaesus wrote: post #74
tbruckner wrote: post #34

Has anyone found these deep research tools useful? In my experience, they generate really bland reports don't go much further than summarization of what a search engine would return.

"Summarization of what a search engine would return" is good enough for many of my purposes though. Good for breaking into new grounds, finding unknown unknowns, brainstorming etc.

I have a script that searches DDG (free), scrapes top 5 results, shoves them into an LLM, and answers your question.

I wrote it back when AI web search was a paid feature and I wanted access to it.

At the time Auto-GPT was popular and using the LLM itself to slowly and unreliably do the research.

So I realized a Python program would be way faster and it would actually be deterministic in terms of doing what you expect.

This experience sort of shaped my attitude about agentic stuff, where it looks like we are still relying too heavily on the LLM and neglecting to mechanize things that could just work perfectly every time.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#129

Post by barrell »

enraged_camel wrote: post #123
barrell wrote: post #108

Earlier quoted context omitted.

> If/when frontier model development speed slows down You do not believe that this has already started? It seems to me that we’re well into a massive slowdown

Not the OP but I use AI all day every day and have noticed substantial improvements in the models over the past ~6 months. GPT-5 was a huge leap (contrary to reporting) and so was Sonnet 4.5.

GPT5 was by no means a huge leap. I’d be willing to believe that you prefer it, or that you found it an improvement, despite both of those being wildly contrary to my experience (and most of the rhetoric online). But objectively speaking it was a small improvement, even going by OpenAI’s marketing claims.

In practice, I upgraded everything to GPT-5 and the performance was so terrible I had to rollback the update.

Re: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch

#130

Post by idiotsecant »

MaxPock wrote: post #95
mike_hearn wrote: post #87

Earlier quoted context omitted.

It's certainly both a lot more than distillation and at least some Chinese labs have been cloning OpenAI via distillation. That's why they instituted much tighter ID verification requirements earlier this year. No, the reason you don't see many open source models coming from the rest-of-world (other than Mistral in France) is that you still need a ton of capital to do it. China can compete because the CCP used a comb…

There’s no Chinese lab that has been accused by OpenAI or anyone else of distillation. The accusations come from fringe right-wing media that are used to the “China only copies” trope. Training a model, by the way, is not about money, because many Western tech giants have more money than the CCP can allocate to Chinese labs. Apple, Meta, Amazon, SAP, IBM, and others have access to the same data as OpenAI and should t…

Oh, wow. 1) you're getting awfully defensive here. I didn't say there was some moral failing because Chinese shops distilled models from western ones. It's the smart play. I'm only commenting on how little of a moat first movers have. 2) if you can't admit that deepseek distilled their models from existing work I'm not sure what to tell you. The early models even identified themselves as chatGPT. It's widely known and has substantial evidence. This isn't team sports, you don't need to play defense. We deal with reality here.
Post reply on HN