pash
@pashmerepat
currently head of ai @cline | prev @meta knowledge graph | creator of vault // @usc alum
Tip: @cline is a free, best-in-class AI coding assistant for @code! It's designed for engineers who value unrestricted access to frontier AI models and comprehensive codebase understanding. On its one year anniversary, it's still my AI-coding tool of choice, with many fans at…
T-11 days till we see Lee back at Vercel
I'm joining Cursor to teach the future of coding! There are millions of developers learning how to use AI and they need pragmatic advice: 1. We need to teach new developers strong foundations, so they know what to learn, and how to solve issues when debugging. 2. We need to…
wow so cool love getting the mysterious micro influencer box that was definitely meant for me
how to get pr packages from ai startups: – tweet about tech - live in sf - be a girl
I was really starting to worry that I wouldn’t receive one of the agentic AI startup illuminati boxes. I bet a lot of you were worried for me too. Good news: we don’t need to worry anymore
Cursor playing checkers, @cline playing chess.
We are experimenting with Pay-As-You-Go at Cerebras! DM me if you want first dibs at trying it
Blocked everyone still posting about the coldplay cam Slop posting for elon bucks is a disease and I’ve found the cure
if you’re a twitter microcelebrity in sf you get pr packages from coding agent startups
"all you ever do is spend time on your phone. you spend more time talking to @growing_daniel and @squirtle_says than to me." - my ex well little does she know that time was well-spent because i now have a mystery box
"Benchmark" from real world jobs!
I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. This is telemetry across all @cline users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error…
“When we launched Zapier, we had no idea who our ICP was” - @mikeknoop, co-founder of @zapier, at @ycombinator this week Early stage startups spend a lot of time obsessing over who their ICP is But sometimes you just have to launch
Let me reiterate this: Cline is THE open source benchmark for agentic code generation performance.
I'd like to point out that for the real world tasks (not benchmarks), Kimi K2 outperforms Gemini. This is telemetry across all @cline users, showing diff edit failure rate. Notice how Kimi has about a 6% failure rate, which is significantly better than Gemini's ~ 10% error…
how retarded do u gotta be to open a mystery box this threatening