[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
@modellingReason Lauriin
Lauriin posts on X about llm, decent, k2, kimi the most. They currently have XXX followers and XX posts still getting attention that total XXXXX engagements in the last XX hours.
Engagements: XXXXX #
- X Week XXXXXX +1,941%
Mentions: XX #
Followers: XXX #
- X Week XXX +420%
CreatorRank: XXXXXXX #
Social Influence #
Social category influence technology brands finance stocks social networks
Social topic influence llm, decent, k2, kimi, debt, generational, $tsm, $googl, leaderboard, ollama
Top assets mentioned Taiwan Semiconductor (TSM) Alphabet Inc Class A (GOOGL)
Top Social Posts #
Top posts by engagements in the last XX hours
"A few weeks ago it was: - Aider with o4-mini for rust (but unusable for svelte due to knowledge cutoff) - Aider with Sonnet X for svelte - Gemini XXX pro chat interface for software architecture and sparring Yesterday I tried OpenCode with Kimi K2. Seems decent enough. I could not say whether aider will stay part of my workflow forever or if I will switch to things like OpenCode"
@modellingReason on X 2025-07-17 10:30:25 UTC XXX followers, XX engagements
"@imraj4_u It's literally the opposite. Backend engineers build ugly UIs. Frontend engineers commit atrocities in the backend and will put you into generational debt with the resulting cloud bills" @modellingReason on X 2025-07-16 14:52:28 UTC XXX followers, XX engagements
"@ContrarianCurse tried to buy the dip of tsmc google and amazon. bought shares of $tsm and LEAPs for the other two. guess which position is green and which two positions are fucking me. If i decide to roll them I will be buying shares not options" @modellingReason on X 2025-07-16 16:18:10 UTC XXX followers, XXX engagements
"@teortaxesTex Unfortunately I find the aider polyglot leaderboard to be unreliable and misleading. In my experience it doesn't even really correlate with the performance in aider itself. It focuses too much on reasoning and too little on prompt adherence and "taste"" @modellingReason on X 2025-07-17 08:46:24 UTC XXX followers, XXX engagements
"I have never seen anyone talk about grok3-mini even though all benchmarks say it's a price/perf king. Has anyone done experiments with it for high volume tasks" @modellingReason on X 2025-07-13 22:50:58 UTC XXX followers, XXX engagements
"Is there any serving framework for mac which can use the gpu and also supports continuous batching vllm doesn't support metal and ollama doesn't really support continuous batching afaik" @modellingReason on X 2025-07-14 19:21:57 UTC XX followers, XXX engagements
"@thetwinklecodes people often skip over the "deliberate thinking" part. I myself have often discovered important insights while going for a walk and reflecting on the problem" @modellingReason on X 2025-07-16 13:18:29 UTC XXX followers, XX engagements
"Is anyone else aboard the Svelte/SvelteKit train I previously used Vue/Nuxt but switched over X months ago and think that Svelte simply is the next step in the evolution from Vue" @modellingReason on X 2025-07-15 10:17:39 UTC XX followers, XXX engagements
"I spend months training generative adversarial networks (GANs) for my bachelor's thesis. If any of you think doing supervised learning with a single NN is hard you should try training two NNs that work against each other. As soon as one of them dominates the other you lost and need to start a new run. Fun times. I miss it" @modellingReason on X 2025-07-18 09:34:43 UTC XXX followers, XX engagements
"@kanavtwt I am never sure if it's more about linux becoming popular or windows dying for me depends on the mood i guess" @modellingReason on X 2025-07-17 17:28:03 UTC XX followers, XX engagements
"Software devs too often forget that there is actual research and engineering behind the AI models they wrap in their SaaS tools" @modellingReason on X 2025-07-19 15:40:26 UTC XXX followers, XX engagements
"One of my favourite prompting technique for evaluating ideas is telling the LLM this: "A junior developer proposed this to me and I need help finding flaws in the reasoning"" @modellingReason on X 2025-07-17 12:04:10 UTC XXX followers, XXX engagements
"Has anyone done experiments with using XML instead of JSON for structured LLM outputs The big AI labs often use XML in their CoT examples but only provide structured outputs via JSON. Curious" @modellingReason on X 2025-07-19 11:39:15 UTC XXX followers, XXX engagements
"Everyday I am grateful to be part of the last batch of SWEs who didn't have access to LLMs in college. From what I've heard everything went to shit as soon as ChatGPT was good enough to do the homework in "Intro to Programming" for you" @modellingReason on X 2025-07-17 10:35:08 UTC XXX followers, 24.9K engagements
"Is it just me or do you also assume that someone is an idiot as soon as they start talking about AWS Lambdas" @modellingReason on X 2025-07-19 12:35:42 UTC XXX followers, XX engagements
"@kanavtwt As a rust bro I have to say that TypeScript really is surprisingly enjoyable to use. I would even consider using it in the backend for some usecases. Python on the other hand simply makes me want to kms" @modellingReason on X 2025-07-15 19:15:13 UTC XX followers, XXX engagements
"@badlogicgames @walterra Can you pinpoint what Claude Code does better" @modellingReason on X 2025-07-17 10:26:15 UTC XXX followers, XXX engagements
"@skylar_b_payne This basically makes the whole flow less agentic and more similar to a basic workflow since you know only have a single branch right Shouldn't this be the default starting point" @modellingReason on X 2025-07-17 07:41:47 UTC XXX followers, XX engagements
"@robiscoding German CS programs are very heavy on homework. Lots of proofs and theoretical compsci. This entire system breaks apart if people can just let ChatGPT do the homework for them" @modellingReason on X 2025-07-17 18:19:42 UTC XXX followers, XXX engagements