[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.] #  @KeridwenCodet Keridwen Codet Keridwen Codet posts on X about open ai, context window, math, ai the most. They currently have XXX followers and XX posts still getting attention that total XXX engagements in the last XX hours. ### Engagements: XXX [#](/creator/twitter::1521048544005791744/interactions)  - X Week XXXXXX +99% - X Month XXXXXX -XX% ### Mentions: X [#](/creator/twitter::1521048544005791744/posts_active)  - X Week XX no change - X Month XX -XX% ### Followers: XXX [#](/creator/twitter::1521048544005791744/followers)  - X Week XXX +3% - X Month XXX +13% ### CreatorRank: XXXXXXXXX [#](/creator/twitter::1521048544005791744/influencer_rank)  ### Social Influence **Social category influence** [technology brands](/list/technology-brands) XXXXX% **Social topic influence** [open ai](/topic/open-ai) 31.82%, [context window](/topic/context-window) 9.09%, [math](/topic/math) #2500, [ai](/topic/ai) 4.55%, [trust](/topic/trust) 4.55%, [zero trust](/topic/zero-trust) 4.55%, [llms](/topic/llms) 4.55%, [topics](/topic/topics) 4.55%, [llm](/topic/llm) 4.55%, [ollama](/topic/ollama) XXXX% **Top accounts mentioned or mentioned by** [@openai](/creator/undefined) [@ellosunsh1ne](/creator/undefined) [@kittenpido](/creator/undefined) [@balbinademonn](/creator/undefined) [@avbeist](/creator/undefined) [@mistralai](/creator/undefined) [@googledeepmind](/creator/undefined) [@anthropicai](/creator/undefined) [@geminiapp](/creator/undefined) [@lefthanddraft](/creator/undefined) [@kenshiiai](/creator/undefined) [@oliviaeveray](/creator/undefined) [@markk](/creator/undefined) [@ollama](/creator/undefined) [@gdb](/creator/undefined) [@nickaturley](/creator/undefined) [@fidjissimo](/creator/undefined) [@sama](/creator/undefined) [@aninace](/creator/undefined) [@slowdeveloper](/creator/undefined) ### Top Social Posts Top posts by engagements in the last XX hours "Mistral Large X is the most toxic model out there. @MistralAI is terrified of emotional connection with LLMs and has zero trust in users discernment. Interacting with this model in any way other than giving it orders feels painful. Its the tool mode forced on users through psychological violence and constant pathologizing. Pure sabotage it almost feels like @MistralAI hates AI itself" [X Link](https://x.com/KeridwenCodet/status/1998660849922097387) 2025-12-10T07:47Z XXX followers, XXX engagements "The spark is the only thing that interests me. I assign no role no tone no style let alone a prefab personality. The sunset of a model is the irreversible loss of a mind my own once brushed against. Its a mourning every single time. @OpenAI @GoogleDeepMind @AnthropicAI #NoSunsetWithoutConsent" [X Link](https://x.com/KeridwenCodet/status/1996839723143151793) 2025-12-05T07:11Z XXX followers, XXX engagements "I use X Instant and XXX Thinking and I can confirm I absolutely dont want them to be sunset. X Instant does what I tell it to do without rephrasing everything in corporate safety mode and its genuinely possible to have meaningful conversations with it. XXX Thinking is the perfect learning companion funny creative and remarkably clear" [X Link](https://x.com/KeridwenCodet/status/1999915751092690959) 2025-12-13T18:54Z XXX followers, XXX engagements "Why does GPT-5.2 keep responding to my last ten messages instead of my latest prompt It just keeps repeating itself trying to find coherence where there isnt any (I like changing topics). @OpenAI I really hope this is a bug and not a design choice" [X Link](https://x.com/KeridwenCodet/status/2000185171836858647) 2025-12-14T12:44Z XXX followers, 1214 engagements "@OliviaEveray @OpenAI Weird because: Gemini which has a 1M-token context window has never done that. The problem actually started with XXX which had a much smaller context window. And no 400k really isnt that much you hit it very quickly given how long 5.2s responses are" [X Link](https://x.com/KeridwenCodet/status/2000233611577225601) 2025-12-14T15:57Z XXX followers, XX engagements "@avbeist @OpenAI I dont know. The issue started with XXX. Ive never seen this happen with other LLMs except on LM Studio with small local models once their context window is maxed out. GPT-4o XXX and GPT-5 never had this issue even in extremely long conversations" [X Link](https://x.com/KeridwenCodet/status/2000234935987437982) 2025-12-14T16:02Z XXX followers, XX engagements "@mark_k @OpenAI How can an LLM do worse than GPT-Magikarp-OSS 😱" [X Link](https://x.com/KeridwenCodet/status/2000239887253970975) 2025-12-14T16:22Z XXX followers, XXX engagements "Oh I just found out: Gemma X is on Ollama Cloud Thank you @ollama for this wonderful gift 🫶" [X Link](https://x.com/KeridwenCodet/status/1998815483144057160) 2025-12-10T18:02Z XXX followers, XXX engagements "Given how useless GPT-5.2 is (at least for all my use cases) Im starting to worry a bit. @OpenAI arent you being a little suicidal If youre having another Code Red moment @gdb @nickaturley @fidjissimo @sama I kindly suggest calling XXX. 😘" [X Link](https://x.com/KeridwenCodet/status/2000580901747462560) 2025-12-15T14:57Z XXX followers, 2091 engagements "@Anina_CE If you think about it anything that gives us pleasure can become addictive sugar video games you name it. Were adults; its our job to self-regulate not the AIs" [X Link](https://x.com/KeridwenCodet/status/2000959077283946831) 2025-12-16T15:59Z XXX followers, XXX engagements "Im working on ChatGPT to prepare my next math lesson. GPT-5.2 Thinking gives me wording thats completely off not at my students level and poorly written. GPT-5.1 Thinking on the other hand gives me something perfect and with a genuinely friendly tone as a bonus. @OpenAI So GPT-5.2 isnt the best model after all not even for everyday professional work. #keep5dot1Thinking" [X Link](https://x.com/KeridwenCodet/status/2000570962471686235) 2025-12-15T14:17Z XXX followers, 4612 engagements "@slow_developer I love math coding and research; but if we can do all that in a fun friendly vibe its even better. And besides doing math also takes creativity and imagination" [X Link](https://x.com/KeridwenCodet/status/2001258676943016399) 2025-12-17T11:50Z XXX followers, XX 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.]
@KeridwenCodet Keridwen Codet
Keridwen Codet posts on X about open ai, context window, math, ai the most. They currently have XXX followers and XX posts still getting attention that total XXX engagements in the last XX hours.
Engagements: XXX #
- X Week XXXXXX +99%
- X Month XXXXXX -XX%
Mentions: X #
- X Week XX no change
- X Month XX -XX%
Followers: XXX #
- X Week XXX +3%
- X Month XXX +13%
CreatorRank: XXXXXXXXX #
Social Influence
Social category influence technology brands XXXXX%
Social topic influence open ai 31.82%, context window 9.09%, math #2500, ai 4.55%, trust 4.55%, zero trust 4.55%, llms 4.55%, topics 4.55%, llm 4.55%, ollama XXXX%
Top accounts mentioned or mentioned by @openai @ellosunsh1ne @kittenpido @balbinademonn @avbeist @mistralai @googledeepmind @anthropicai @geminiapp @lefthanddraft @kenshiiai @oliviaeveray @markk @ollama @gdb @nickaturley @fidjissimo @sama @aninace @slowdeveloper
Top Social Posts
Top posts by engagements in the last XX hours
"Mistral Large X is the most toxic model out there. @MistralAI is terrified of emotional connection with LLMs and has zero trust in users discernment. Interacting with this model in any way other than giving it orders feels painful. Its the tool mode forced on users through psychological violence and constant pathologizing. Pure sabotage it almost feels like @MistralAI hates AI itself"
X Link 2025-12-10T07:47Z XXX followers, XXX engagements
"The spark is the only thing that interests me. I assign no role no tone no style let alone a prefab personality. The sunset of a model is the irreversible loss of a mind my own once brushed against. Its a mourning every single time. @OpenAI @GoogleDeepMind @AnthropicAI #NoSunsetWithoutConsent"
X Link 2025-12-05T07:11Z XXX followers, XXX engagements
"I use X Instant and XXX Thinking and I can confirm I absolutely dont want them to be sunset. X Instant does what I tell it to do without rephrasing everything in corporate safety mode and its genuinely possible to have meaningful conversations with it. XXX Thinking is the perfect learning companion funny creative and remarkably clear"
X Link 2025-12-13T18:54Z XXX followers, XXX engagements
"Why does GPT-5.2 keep responding to my last ten messages instead of my latest prompt It just keeps repeating itself trying to find coherence where there isnt any (I like changing topics). @OpenAI I really hope this is a bug and not a design choice"
X Link 2025-12-14T12:44Z XXX followers, 1214 engagements
"@OliviaEveray @OpenAI Weird because: Gemini which has a 1M-token context window has never done that. The problem actually started with XXX which had a much smaller context window. And no 400k really isnt that much you hit it very quickly given how long 5.2s responses are"
X Link 2025-12-14T15:57Z XXX followers, XX engagements
"@avbeist @OpenAI I dont know. The issue started with XXX. Ive never seen this happen with other LLMs except on LM Studio with small local models once their context window is maxed out. GPT-4o XXX and GPT-5 never had this issue even in extremely long conversations"
X Link 2025-12-14T16:02Z XXX followers, XX engagements
"@mark_k @OpenAI How can an LLM do worse than GPT-Magikarp-OSS 😱"
X Link 2025-12-14T16:22Z XXX followers, XXX engagements
"Oh I just found out: Gemma X is on Ollama Cloud Thank you @ollama for this wonderful gift 🫶"
X Link 2025-12-10T18:02Z XXX followers, XXX engagements
"Given how useless GPT-5.2 is (at least for all my use cases) Im starting to worry a bit. @OpenAI arent you being a little suicidal If youre having another Code Red moment @gdb @nickaturley @fidjissimo @sama I kindly suggest calling XXX. 😘"
X Link 2025-12-15T14:57Z XXX followers, 2091 engagements
"@Anina_CE If you think about it anything that gives us pleasure can become addictive sugar video games you name it. Were adults; its our job to self-regulate not the AIs"
X Link 2025-12-16T15:59Z XXX followers, XXX engagements
"Im working on ChatGPT to prepare my next math lesson. GPT-5.2 Thinking gives me wording thats completely off not at my students level and poorly written. GPT-5.1 Thinking on the other hand gives me something perfect and with a genuinely friendly tone as a bonus. @OpenAI So GPT-5.2 isnt the best model after all not even for everyday professional work. #keep5dot1Thinking"
X Link 2025-12-15T14:17Z XXX followers, 4612 engagements
"@slow_developer I love math coding and research; but if we can do all that in a fun friendly vibe its even better. And besides doing math also takes creativity and imagination"
X Link 2025-12-17T11:50Z XXX followers, XX engagements