𝖓𝖊𝖚𝖙𝖗𝖆𝖑

13 posts

𝖓𝖊𝖚𝖙𝖗𝖆𝖑 banner
𝖓𝖊𝖚𝖙𝖗𝖆𝖑

𝖓𝖊𝖚𝖙𝖗𝖆𝖑

@neutral

intern @lute

เข้าร่วม Ağustos 2022
31 กำลังติดตาม356 ผู้ติดตาม
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
Bridging slows you down and introduces risk. Lute lets you trade across chains in one click. Faster execution with no extra steps.
English
13
5
56
2.5K
Andrej Karpathy
Andrej Karpathy@karpathy·
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 github.com/karpathy/llm-c… if others would like to play. ty nano banana pro for fun header image for the repo
Andrej Karpathy tweet media
Andrej Karpathy@karpathy

I’m starting to get into a habit of reading everything (blogs, articles, book chapters,…) with LLMs. Usually pass 1 is manual, then pass 2 “explain/summarize”, pass 3 Q&A. I usually end up with a better/deeper understanding than if I moved on. Growing to among top use cases. On the flip side, if you’re a writer trying to explain/communicate something, we may increasingly see less of a mindset of “I’m writing this for another human” and more “I’m writing this for an LLM”. Because once an LLM “gets it”, it can then target, personalize and serve the idea to its user.

English
904
1.5K
16.9K
5.3M
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
10,000 trading faster, smarter, and together. 10,000 realized why we lead. 10,000 followers on Lute. Growth like this doesn’t happen by accident.
LUTE tweet media
English
248
77
486
45.7K
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
Seamless crosschain trading is now live on Lute Buy crosschain in one click using SOL or ETH without having to worry about manually bridging or funding wallets on new chains ever again Our next step towards trading anything on Lute
LUTE tweet media
English
233
81
512
60.8K
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
Who are you trading with?
LUTE tweet media
English
278
65
547
149.1K
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
it pays to be early
English
558
169
1.4K
183.1K
𝖓𝖊𝖚𝖙𝖗𝖆𝖑 รีทวีตแล้ว
LUTE
LUTE@lute·
our first official partner goes live on day 1
English
297
132
1.2K
123.6K
WGI | Neutral
WGI | Neutral@OfficialNeutral·
Neutral for the love of God give me this @ it's not even good for ur brand please
English
1
0
6
503