# ![@dvddkkim Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1363908357166411778.png) @dvddkkim David Kim

David Kim posts on X about braintrust, prompt, faster, token the most. They currently have [---] followers and [--] posts still getting attention that total [--] engagements in the last [--] hours.

### Engagements: [--] [#](/creator/twitter::1363908357166411778/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1363908357166411778/c:line/m:interactions.svg)

- [--] Week [--] -85%
- [--] Month [-----] +3,817%
- [--] Months [-----] +96,883%

### Mentions: [--] [#](/creator/twitter::1363908357166411778/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1363908357166411778/c:line/m:posts_active.svg)

- [--] Week [--] no change
- [--] Month [--] no change
- [--] Months [--] +800%

### Followers: [---] [#](/creator/twitter::1363908357166411778/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1363908357166411778/c:line/m:followers.svg)

- [--] Months [---] +23%

### CreatorRank: undefined [#](/creator/twitter::1363908357166411778/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1363908357166411778/c:line/m:influencer_rank.svg)

### Social Influence

**Social category influence**
[cryptocurrencies](/list/cryptocurrencies)  [finance](/list/finance) 

**Social topic influence**
[braintrust](/topic/braintrust) #21, [prompt](/topic/prompt) #889, [faster](/topic/faster), [token](/topic/token), [if you](/topic/if-you), [ai](/topic/ai), [for all](/topic/for-all), [loop](/topic/loop)

**Top accounts mentioned or mentioned by**
[@braintrust](/creator/undefined) [@realmcore](/creator/undefined) [@reneeshah123](/creator/undefined) [@braintrustdata](/creator/undefined) [@jennife89269163](/creator/undefined)

**Top assets mentioned**
[Braintrust (BTRST)](/topic/braintrust)
### Top Social Posts
Top posts by engagements in the last [--] hours

"o3 is the bro I'm studying for my cs exam with. Claude [--] is the bro I'm pulling up to hoop with"  
[X Link](https://x.com/dvddkkim/status/1946785230859423982)  2025-07-20T04:12Z [--] followers, [--] engagements


"@reneeshah123 @braintrustdata https://www.braintrust.dev/blog/brainstore https://www.braintrust.dev/blog/brainstore"  
[X Link](https://x.com/dvddkkim/status/1981936609982587116)  2025-10-25T04:11Z [--] followers, [---] engagements


"So much UX possibilities with low latency models"  
[X Link](https://x.com/dvddkkim/status/1986652001220866185)  2025-11-07T04:28Z [--] followers, [--] engagements


"It was so fun working on this with the team :) If you want to work on AI tooling and/or AI where you have autonomy with teammates who trust and support you we are hiring for all roles (If you are a designer who codes interested -- I'm happy to chat and share my exp. dm me) Production AI breaks in unexpected ways. Loop helps you figure out what happened and what to fix fast. https://t.co/rXG1MKUCyh Production AI breaks in unexpected ways. Loop helps you figure out what happened and what to fix fast. https://t.co/rXG1MKUCyh"  
[X Link](https://x.com/dvddkkim/status/1993404529623417332)  2025-11-25T19:40Z [--] followers, [--] engagements


"@realmcore_ @braintrust examples of other co's sharing the evals/experiments visualization https://x.com/kamathematic/status/1911861870283333990 GPT-4.1 is a DOWNGRADE for Stagehand New models seem to be getting "smarter" and more creative often at the cost of actually doing a specific task with a specific outcome. Gemini is still the cheapest fastest and most accurate. 4.1-nano is cheaper/faster but dumber. https://t.co/Dirv0s2S2F https://x.com/kamathematic/status/1911861870283333990 GPT-4.1 is a DOWNGRADE for Stagehand New models seem to be getting "smarter" and more creative often at the"  
[X Link](https://x.com/dvddkkim/status/1996313520636613047)  2025-12-03T20:20Z [--] followers, [---] engagements


"@realmcore_ @braintrust I've been dogfooding Braintrust to eval our agent and it's been working well for me For our agent i do most of the eval through the SDK. We built a cli version of our agent set up an eval env using the sdk and throw whatever eval task at it"  
[X Link](https://x.com/dvddkkim/status/1996326699307335998)  2025-12-03T21:12Z [--] followers, [--] engagements


"@realmcore_ @braintrust what have you had problems with happy to help"  
[X Link](https://x.com/dvddkkim/status/1996326803619590190)  2025-12-03T21:12Z [--] followers, [--] engagements


"gpt-5.2 performed slightly better on our prompt optimization evals but gpt-5.1 was faster and more token efficient evals powered by @braintrust"  
[X Link](https://x.com/dvddkkim/status/1999311116565119029)  2025-12-12T02:51Z [---] followers, [----] engagements


"We recently added support for SQL at @braintrust I thought our agent Loop would be better out of the box at generating SQL over our own query language (BTQL) given that's what models are trained on. Surprisingly this wasn't the case because our harness was optimized for generating BTQL. With some tweaks to our tool implementation and prompt guided by evals we were able to turn that around https://twitter.com/i/web/status/2012327070286893332 https://twitter.com/i/web/status/2012327070286893332"  
[X Link](https://x.com/dvddkkim/status/2012327070286893332)  2026-01-17T00:52Z [---] followers, [----] engagements


"I compared Kimi K2.5 to Sonnet [---] to see which is better at prompt optimization using @braintrust I gave it [--] scenarios -- ranging from movie guessing to sql gen. Sonnet came out slightly on top improving score by 54.6% on average across multiple runs. However time to first token for Kimi K2.5 was [--] times faster than Sonnet https://twitter.com/i/web/status/2016312930397204839 https://twitter.com/i/web/status/2016312930397204839"  
[X Link](https://x.com/dvddkkim/status/2016312930397204839)  2026-01-28T00:50Z [---] followers, [---] engagements

Limited data mode. Full metrics available with subscription: lunarcrush.com/pricing