Viewing profile — Sai_Praneeth
Sai_Praneeth
HN member- Joined
- Wed, Jun 30, 2021, 7:50 PM UTC
- HN karma
- 14
- Public activity
- 26 items
- HN profile
- View on Hacker News ↗
About Sai_Praneeth
https://saipraneeth.in
Recent public activity
-
story
Show HN: Lazarus, a coding agent for long-horizon tasks
I have been interested in long-horizon coding tasks for a while, especially with benchmarks like FrontierSWE, where even the best coding agents like Codex and Claude Code struggle …
-
comment
Comment #46630301
https://saipraneeth.in
- story
-
story
Show HN: modal-cuda – CLI to run CUDA .cu programs on Modal GPUs
I use a MacBook (no NVIDIA GPU) but still like experimenting with CUDA kernels. I didn’t want to spin up a VM every time or use browser-only tools, so I built a tiny CLI that runs …
-
story
Show HN: Elliot – my coding agent that helps me code, and sometimes helps itself
Built a coding agent that's actually useful for working with existing codebases - the kind where you need to understand structure, not just append code. Key capabilities: - Structu…
- story
-
comment
Comment #44096738
i haven't used cursor or codex or any system that says "agentic coding experience" i speak in thoughts in my head and it is better to just translate those thoughts to code directly…
-
comment
Comment #44087914
I built this as a weekend experiment to see how far you can push a basic LZ-style compressor using LLM-guided code mutations. No fancy ML models here—just a simple loop: mutate, ev…
- story
-
story
Show HN: Zeno – A framework for verifiable RL rewards (code, math, and more)
With TRL, it's now straightforward to RL-finetune LLMs, but picking good reward functions is still the weakest link. Zeno is an open-source toolkit for verifiable, deterministic re…
-
story
Show HN: Open-Source AlphaEvolve Clone Using GPT-4.1 and Genetic Programming
Everyone saw the AlphaEvolve hype. I got obsessed with how it might work under the hood and decided to just build it myself. My setup uses GPT-4.1 to mutate matrix multiplication c…
-
story
Show HN: Raman-01 – A Pocket Physics Solver LLM
I built a tiny physics solver LLM that performs surprisingly well on easy-to-medium difficulty physics problems. Most LLMs today still struggle with physics QA (as PhyBench recentl…
-
comment
Comment #43841060
idk if this is only for me or happened to others as well, apart from the glaze, the model also became a lot more confident, it didn't use the web search tool when something out of …
- story
-
story
Show HN: Showdown of Titans: GPT-4o vs. DeepSeek V3 in AI Debate Arena
Just launched AI Agents Debate Arena – a battleground where OpenAI’s GPT-4o and DeepSeek’s V3 go head-to-head in real-time debates! Users can either pick from AI-suggested topics o…
-
comment
Comment #42841227
wow nice
-
story
Show HN: Built a retro text adventure using V0 and OpenAI
I created a classic text-based adventure game inspired by Zork using Vercel's v0. Each refresh generates a unique game title, setting, and context, with AI handling the dynamic sto…
-
comment
Comment #42840618
aahh damn, thanks i just typed the objective, it solved the game, stupid openai fixing it
- story
-
comment
Comment #42840551
Updated link to the game: https://uj0gnt8ewsnqdwnf.vercel.app/
-
comment
Comment #42840519
hi, thanks for trying it out, redeployed after fixing the error check it out here: https://awng08bk1cxj8ydx.vercel.app/
-
story
Show HN: Retro text adventure game built using V0 and OpenAI
I created a classic text-based adventure game inspired by Zork using Vercel's v0. Each refresh generates a unique game title, setting, and context, with AI handling the dynamic sto…
- comment
-
comment
Comment #41643627
Retrieval Augmented Generation. Fancy way of saying, retrieve chunks from your document corpus similar to your input using a similarity (mostly cosine) of embedding vectors of the …
-
comment
Comment #41599230
Wow this looks clean (no pun intended). Great speedups as well!