Ask HN: Which LLM are you using to evaluate your ideas?

#1

Post by Marius77 » Sun, May 10, 2026, 9:14 PM UTC

Question as in the title. Curious about your experience and which LLM helped you out the most without saying yes to everything..

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#2

Post by apparent » Sun, May 10, 2026, 9:44 PM UTC

I am mostly using Gemini, but that's a decision I made 2-3 months ago. I try my best not to hint at what answer I am hoping for/would benefit me, and I play devil's advocate as much as possible.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#3

Post by thisisauserid » Sun, May 10, 2026, 10:35 PM UTC

apparent wrote: post #2

I am mostly using Gemini, but that's a decision I made 2-3 months ago. I try my best not to hint at what answer I am hoping for/would benefit me, and I play devil's advocate as much as possible.

I only use Gemini 3.1 Pro. In my opinion, it's is better/cheaper/faster.

I'm not coding with it much.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#4

Post by moduxis » Mon, May 11, 2026, 12:49 AM UTC

For now, I'd say Claude. I tried to work with other LLMs such as Gemini, Codex, GPT and Grok(high versions), but still Claude (4.8) gave me the best outcome.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#5

Post by quintes » Mon, May 11, 2026, 1:34 AM UTC

I actually haven’t gotten to evaluating ideas yet I’ve been too busy asking each llm why they thought they would be best for the task. Just kidding

I use ChatGPT and Gemini and Claude in various ways in my workflow

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#6

Post by Jinyibruceli » Mon, May 11, 2026, 3:28 AM UTC

[flagged]

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#7

Post by borealbuilder » Mon, May 11, 2026, 4:27 AM UTC

I landed with Claude as my daily driver LLM. As it is still limited in some capacities I do also work with ChatGPT and Gemini where they give better results in specific circumstances.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#8

Post by warren455 » Mon, May 11, 2026, 8:58 AM UTC

I’ve started using different models for different stages.

GPT mostly for product direction and positioning discussions. Codex for implementation-heavy changes and large refactors. v0 more for landing page structure / UI iteration.

I still find product judgment and SEO decisions require a lot of manual thinking though.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#9

Post by gajo357 » Mon, May 11, 2026, 12:48 PM UTC

Manus was great, used it for months for exploring ideas, making reports and such. I dropped it when I heard that Meta was buying it.

Then I used Gemini and it was great as well, but very limited when it comes to coding (in Antigravity) because instead of giving me credits for coding in the subscription they give you GB on Google Drive. So you burn through the coding very quickly.

Github Copilot is the worst. It usually gets lost while editing some file. And it is incredibly slow.

Then I swithced to Codex and ChatGPT. Great combo for everything. Good at coding, good at exploring, generous with limits (much more so the first month).

I haven't used Claude Code directly, but Claude Opus 4.x was probably the best model for coding used via Copilot and Antigravity.

Re: Ask HN: Which LLM are you using to evaluate your ideas?

#10

Post by shouvik12 » Mon, May 11, 2026, 2:58 PM UTC

I use Claude for initial idea validation.It is decent. For iteration and refinement, I route simpler clarifications through local models (Qwen via Ollama)