[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.] #  @DSPyOSS DSPy DSPy posts on X about llm, algo, context window, all the the most. They currently have XXXXX followers and XX posts still getting attention that total XXXXX engagements in the last XX hours. ### Engagements: XXXXX [#](/creator/twitter::1915045571485990912/interactions)  - X Week XXXXXX +58% - X Month XXXXXXX +26% ### Mentions: X [#](/creator/twitter::1915045571485990912/posts_active)  - X Week XX +28% - X Month XX +165% ### Followers: XXXXX [#](/creator/twitter::1915045571485990912/followers)  - X Week XXXXX +4.40% - X Month XXXXX +20% ### CreatorRank: XXXXXXX [#](/creator/twitter::1915045571485990912/influencer_rank)  ### Social Influence [#](/creator/twitter::1915045571485990912/influence) --- **Social category influence** [technology brands](/list/technology-brands) [social networks](/list/social-networks) **Social topic influence** [llm](/topic/llm), [algo](/topic/algo), [context window](/topic/context-window), [all the](/topic/all-the), [rage](/topic/rage), [realise](/topic/realise), [context engineering](/topic/context-engineering), [linkedin](/topic/linkedin) ### Top Social Posts [#](/creator/twitter::1915045571485990912/posts) --- Top posts by engagements in the last XX hours "The core of dspy.SIMBA aligns perfectly with @karpathy's quote: do rollouts stuff them into one context window (along with the rewards) review/reflect on what went well or not to obtain string "lesson" to be added to system prompt But there's plenty more in the algo"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1944533892096209295) 2025-07-13 23:06:22 UTC 7650 followers, 6296 engagements "Andrej really should pick up some DSPy :D"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1944438422124327331) 2025-07-13 16:47:00 UTC 7658 followers, 3527 engagements "Awesome to see Amazon AWS build on DSPy to help their customers for prompt migration 👀 Delivering up to XX% gains in their evals"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1946204351472529767) 2025-07-18 13:44:10 UTC 7668 followers, 17K engagements "@sergeykarayev There are dozens and dozens. We post them literally all the time. Just scroll @DSPyOSS. Will collect a few examples for you below There's no such thing as the DSPy team really. Almost everyone you see on here are regular users who love the framework"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1946337099285704991) 2025-07-18 22:31:40 UTC 7654 followers, 8540 engagements "Yes this is a description of how the dspy.SIMBA optimizer works. a review/reflect stage along the lines of "what went well what didn't go so well what should I try next time" etc. and the lessons from this stage feel explicit like a new string to be added to the system prompt for the future optionally to be distilled into weights (/intuition) later a bit like sleep. Distilling through the weights is the dspy.BetterTogether strategy"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1944437156673474705) 2025-07-13 16:41:58 UTC 7668 followers, 74.8K engagements "😂 hilarious & insightful post "Context Engineering is. Wait. I just described programming 🤯. How long till people realise this and switch to @DSPyOSS""  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1945428389734568367) 2025-07-16 10:20:47 UTC 7650 followers, 2966 engagements "DSPy: Replacing LLM Musings with Modules at the @pyowa meetup today"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1947865015739981894) 2025-07-23 03:43:03 UTC 7668 followers, 5032 engagements "University of Maryland researchers introduce AegisLLM a new agentic system for LLM security like defending against jailbreaks. Leveraging DSPy AegisLLM *evolves* based on the attacks it sees in real timevia dspy.MIPROv2 prompt optimization. Up to XX% in optimization gains"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1944754829093392416) 2025-07-14 13:44:17 UTC 7648 followers, 6867 engagements "8+ years of experience with DSPy in demand yall better get started LinkedIn wont wait"  [@DSPyOSS](/creator/x/DSPyOSS) on [X](/post/tweet/1944496298142376410) 2025-07-13 20:36:59 UTC 7667 followers, 5673 engagements
[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.]
DSPy posts on X about llm, algo, context window, all the the most. They currently have XXXXX followers and XX posts still getting attention that total XXXXX engagements in the last XX hours.
Social category influence technology brands social networks
Social topic influence llm, algo, context window, all the, rage, realise, context engineering, linkedin
Top posts by engagements in the last XX hours
"The core of dspy.SIMBA aligns perfectly with @karpathy's quote: do rollouts stuff them into one context window (along with the rewards) review/reflect on what went well or not to obtain string "lesson" to be added to system prompt But there's plenty more in the algo" @DSPyOSS on X 2025-07-13 23:06:22 UTC 7650 followers, 6296 engagements
"Andrej really should pick up some DSPy :D" @DSPyOSS on X 2025-07-13 16:47:00 UTC 7658 followers, 3527 engagements
"Awesome to see Amazon AWS build on DSPy to help their customers for prompt migration 👀 Delivering up to XX% gains in their evals" @DSPyOSS on X 2025-07-18 13:44:10 UTC 7668 followers, 17K engagements
"@sergeykarayev There are dozens and dozens. We post them literally all the time. Just scroll @DSPyOSS. Will collect a few examples for you below There's no such thing as the DSPy team really. Almost everyone you see on here are regular users who love the framework" @DSPyOSS on X 2025-07-18 22:31:40 UTC 7654 followers, 8540 engagements
"Yes this is a description of how the dspy.SIMBA optimizer works. a review/reflect stage along the lines of "what went well what didn't go so well what should I try next time" etc. and the lessons from this stage feel explicit like a new string to be added to the system prompt for the future optionally to be distilled into weights (/intuition) later a bit like sleep. Distilling through the weights is the dspy.BetterTogether strategy" @DSPyOSS on X 2025-07-13 16:41:58 UTC 7668 followers, 74.8K engagements
"😂 hilarious & insightful post "Context Engineering is. Wait. I just described programming 🤯. How long till people realise this and switch to @DSPyOSS"" @DSPyOSS on X 2025-07-16 10:20:47 UTC 7650 followers, 2966 engagements
"DSPy: Replacing LLM Musings with Modules at the @pyowa meetup today" @DSPyOSS on X 2025-07-23 03:43:03 UTC 7668 followers, 5032 engagements
"University of Maryland researchers introduce AegisLLM a new agentic system for LLM security like defending against jailbreaks. Leveraging DSPy AegisLLM evolves based on the attacks it sees in real timevia dspy.MIPROv2 prompt optimization. Up to XX% in optimization gains" @DSPyOSS on X 2025-07-14 13:44:17 UTC 7648 followers, 6867 engagements
"8+ years of experience with DSPy in demand yall better get started LinkedIn wont wait" @DSPyOSS on X 2025-07-13 20:36:59 UTC 7667 followers, 5673 engagements
/creator/twitter::DSPyOSS