
Tzvi Melamed
@TzviPM
Followers
14
Following
23
Media
3
Statuses
146
Joined September 2024
I'm trying out the new CLI from @cursor_ai with GPT-5 from @OpenAI running inside of a @github codespace. Its taking longer than I'm used to with @AnthropicAI's claude code, but it runs on my very mediocre laptop (a la codespace) and is quite good. Thanks @leerob for tipping me.
0
0
0
If anyone is looking for a talented software engineer to take their business, project, or team to the next level, please consider me for the job :)
tzvipm.dev
Hi, I'm Tzvi. I'm a husband, dad, software developer, lifelong learner, and maker of puns. Come say hi! I'm @TzviPM on Github and Twitter.
0
0
0
Today is my first day post-layoff from @Blazesoftltd. It was a wild ride and a pleasure to work with such passionate and dedicated people. It really did feel like a family working there and I've been overwhelmed by people messaging me on LinkedIn and calling me to wish me well.
0
0
0
Fresh off the press: This is a neat variation of @martinfowler's replace conditional with polymorphism with more of a structural approach.
tzvipm.dev
Hi, I'm Tzvi. I'm a husband, dad, software developer, lifelong learner, and maker of puns. Come say hi! I'm @TzviPM on Github and Twitter.
0
0
0
I feel like react server components provide a horrendous developer experience and encourage premature optimization. They attempt to obscure essential complexity while over-complicating the simple. Someone please change my mind. @leerob @_developit @ryanflorence.
0
0
0
I've been using claude code from @AnthropicAI a lot lately and I noticed that I don't get the completions or aliases from .zshrc file but I do get your .zprofile. I (claude actually) recently moved all of my non-TTY specific config to .zprofile. I highly recommend It 😅.
0
0
0
“LLMs Get Lost In Multi-Turn Conversation” by Philippe Laban, Hiroaki Hayashi, Yingbo Zhou, Jennifer Neville seems to me one of the most pivotal and yet under-appreciated papers of this age .
arxiv.org
Large Language Models (LLMs) are conversational interfaces. As such, LLMs have the potential to assist their users not only when they can fully specify the task at hand, but also to help them...
0
3
13