Live data from Hacker News

Gemini 2.5 Deep Think

blog.google

1–10 of 259 posts

Re: Gemini 2.5 Deep Think

#3
Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

Re: Gemini 2.5 Deep Think

#4

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

Yeah the general “discovery” is that using the same reasoning compute effort, but spreading them over multiple different agents generally leads to better results.

It solves the “longer thinking leads to worse results” problem by approaching multiple paths of thinking in parallel, but just not think as long.

Re: Gemini 2.5 Deep Think

#7

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

I am surprised such a simple approach has taken so long to be actually used. My first image description cli attempt did basically that: Use n to get several answers and another pass to summarize.

Re: Gemini 2.5 Deep Think

#8
post #7

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

I am surprised such a simple approach has taken so long to be actually used. My first image description cli attempt did basically that: Use n to get several answers and another pass to summarize.

It's very resource intensive so maybe they had to wait until processes got more efficient? I can also imagine they would want to try and solve it in a... better way before doing this.

Re: Gemini 2.5 Deep Think

#10
post #7

Approach is analogous to Grok 4 Heavy: use multiple "reasoning" agents in parallel and then compare answers before coming back with a single response, taking ~30 minutes. Great results, though it would be more fair for the benchmark comparisons to be against Grok 4 Heavy rather than Grok 4 (the fast, single-agent model).

I am surprised such a simple approach has taken so long to be actually used. My first image description cli attempt did basically that: Use n to get several answers and another pass to summarize.

I agree but I think its hard to get a sufficient increase in performance that would justify 3-4x increase in cost.
Post reply on HN