Viewing profile — binalpatel

Made this as a side-quest, simple way to allow agents to self-register, interact, and poll a Discord channel (alongside human interactions). Largely interested in seeing how groups…

The agent making it's own harness idea is really powerful, I gave it a try here with some opinionated choices: https://github.com/caesarnine/binsmith Been running it on a locked do…

This is admittedly dated but even back in December 2023 GPT-4 with it's Vision preview was able to very reliably do structured extraction, and I'd imagine Gemini 3 Flash is much be…

It reuses previously generated code, so tools it creates persists from session to session. It also lets the LLM avoid actually “seeing” the tokens in some cases since it can pipe d…

I've been using it daily, so far it's built CLIs for hackernews, BBC news, weather, a todo manager, fetching/parsing webpages etc. I asked it to make a daily briefing one that just…

I went down (continue to do down) this rabbit hole and agree with the author. I tried a few different ideas and the most stable/useful so far has been giving the agent a single run…

100% - sharing CLIs with the agent has felt like another channel to interact with them once I’ve done it enough, like a task manager the agent and I can both use using the same int…

Cool to see lots of people independently come to "CLIs are all you need". I'm still not sure if it's a short-term bandaid because agents are so good at terminal use or if it's part…

Built this for myself but thought it was useful enough to share. It's essentially a server/client setup that lets you plug in arbitrary Pydantic-AI agents. All the state is handled…

Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, f…

Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, f…

Pydantic-AI is lovely - I've been working on a forever, fun project to build a coding agent CLI for a year plus now. IMO it does make constructing any given agent very easy, though…

This is super impressive. Interesting they're framing this more from the world model/agent environment angle, when this seems like the best example so far of generative games. 720p…

Under $100: The heat gun mosquito things that some tech folks were mentioning on Twitter. Always get quarter sized terribly itchy bumps for each mosquito bites and using it makes t…

This is going to wreck Goldman's next analysis. (context: https://the-decoder.com/goldman-sachs-blunder-adds-to-ai-sto... )

https://newsletter.pessimistsarchive.org/p/slide-rule-fast-a... Same energy

My personal (overly biased view after reading Chip War recently) take is pretty much there, seems like a lot of the same early dynamics of semiconductors are playing out here. Very…

Agreed with both - #1 especially: https://www.propublica.org/article/philips-kept-warnings-abo...

One fun detail - I don't know any Typescript nor have I ever coded a VSCode extension before, so this was all made going back and forth with Sonnet 3.5 + digging through the VSCode…

Fun little project I created with Sonnet 3.5 in a few hours. Essentially exploring the idea of a coding assistant that can interact with the workspace and run shell commands withou…

Virtual actors are so nice, Dapr[1] uses them as well. You can get hack together something like a virtual actor with Ray too but I'm hoping their actors eventually evolve into some…

You can do some really cool things now with these models, like ask them to extract not just the text but figures/graphs as nodes/edges and it works very well. Back when GPT-4 with …

Gemini 1.5 Pro is really good at long context in my experience.

Here's a direct link to the code: https://github.com/caesarnine/llm-experiments/blob/main/3_st... Just a Pydantic model to define an extraction schema + a simple prompt works reaso…