As a fun Saturday vibe code project and following up on this tweet earlier, I hacked up an **llm-council** web app. It looks exactly like ChatGPT except each user query is 1) dispatched to multiple models on your council using OpenRouter, e.g. currently:
"openai/gpt-5.1",
"google/gemini-3-pro-preview",
"anthropic/claude-sonnet-4.5",
"x-ai/grok-4",
Then 2) all models get to see each other's (anonymized) responses and they review and rank them, and then 3) a "Chairman LLM" gets all of that as context and produces the final response.
It's interesting to see the results from multiple models side by side on the same query, and even more amusingly, to read through their evaluation and ranking of each other's responses.
Quite often, the models are surprisingly willing to select another LLM's response as superior to their own, making this an interesting model evaluation strategy more generally. For example, reading book chapters together with my LLM Council today, the models consistently praise GPT 5.1 as the best and most insightful model, and consistently select Claude as the worst model, with the other models floating in between. But I'm not 100% convinced this aligns with my own qualitative assessment. For example, qualitatively I find GPT 5.1 a little too wordy and sprawled and Gemini 3 a bit more condensed and processed. Claude is too terse in this domain.
That said, there's probably a whole design space of the data flow of your LLM council. The construction of LLM ensembles seems under-explored.
I pushed the vibe coded app to
https://t.co/EZyOqwXd2k
if others would like to play. ty nano banana pro for fun header image for the repo
@RockstarGames@ashskyqueen@ashskyqueen this video is atleast worth a million views. (That is minimum). Incredible video. Thanks โค๏ธ for such amazing efforts. ๐
@shakteed @gokulr Engineering productivity is measured at a team level by tracking sprint velocity, deliverables, JIRA tickets. This has ever been a challenge for managers & enterprises.
Making it easier and safer, @BlueOptima has transparent metrics & AI to help improve productivity & quality.
Low code and no code solutions are on the rise as organisations are wanting to improve software development capacity.
Learn more: https://t.co/iSiLojI3Ie
Women remain vastly underrepresented in the technology industry, only accounting for just 8% of positions in #softwaredevelopment.
What initiatives are organisations using to improve diversity in #SoftwareEngineering teams? #womenintech
Read more: https://t.co/pL4o1f6SMR
@HyundaiIndia@AdvaithHyundai@hyundai_kun Update:
Hyundai India has finally replied back, Now they are carrying out the vehicle repair to diagnose the problem in coordination with Kun Hyundai at Hyundai's cost. ETD stated to be 21st Nov. Hoping to get a postive outcome for the issue faced by multiple Creta owners.
@kishanraj814@HyundaiIndia@AdvaithHyundai@hyundai_kun Lets see, so far I am disappointed, they had escalated the issue till regional dealer level, and they tried to close the case saying, lets repair the car and go on a 200km ride to test the brakes (just wow). Have mailed the report to @HyundaiIndia again. Waiting with hopes. :)
@VijayAg56298494@HyundaiIndia@hyundaiceo@VijayAg56298494 I have also met with the same faith with my creta. And my grandfather was the victim. And whats the solution the company has offered to you? Because this is a serious issue.