Buy A Modem

Show HN: I Derived a Steak

After years of juggling imprecise grilling recipes and temperatures, I've made a grilling calculator that derives perfect meat results from thermal models, Fick's law of diffusion, protein structures, and more.Along the way I calculated exactly how far in advance to salt meat (spoiler: even when it's frozen!), realized the best dry brine is usually "cling brine" (covered), derived approximate charcoal quantities with physics, and much more.As with the pancake calculator[

Show HN: FPGA design acceleration – idiomatic Python to synthesizable Verilog

Recently I've been working on a certain embedded system that has an FPGA running EKF and some controls. Coding that in RTL is inefficient at best so I turned to HLS and looked around to see what the industry has to offer. I have a pretty extensive simulation and verification scaffold in Python, so ideally I wanted something that can accept Python directly, preferably with minimal adaptation, so that I could feed relevant parts of my Python models to the HLS tool and immediately get a workin

Show HN: Even, the terminal-first desktop workspace

If you’re like me and have basically delegated all your development to Claude code, Codex, OpenCode and the other agents, you’d agree that one of the annoying things is the unmanageable terminals. Personally I love working on the terminal, but when building multiple projects, it quickly becomes messy.I built Even to solve this mess. I can control my terminal tabs per project, + comes with some nice features that make it so I don’t need to open any other app when locked in.In built Browser, Agent

Show HN: Caliper – pass@k reliability testing for Claude Code and Codex skills

Skills for Claude Code and Codex are hard to test. What I mean by hard is that there's no standard way to do it. You evaluate the skill once on something, it looks like it works. You publish it. Then the new super model releases (GLM 5.2 anyone?), it will quietly break for some part, and you won't find out until your users complain.I also faced the same problem, so I tried to build something lightweight to stop doing that. Caliper.It's a local and lightweight harness that runs a s

Ask HN: Best local LLM under 2B paramater and consuming RAM less than 3gb

For my local project, I have been finding a good LLM or a SLM that consumes less than 2gb ram, can you get me any models that would aid me?

Show HN: role-model, a router for hybrid local/cloud AI

Hey everyone, I'm launching role-model today: a routing protocol, a reference router runtime, and an extension for Pi that allows for better informed routing decisions.role-model is mostly deterministic, with fallback to a controller model, that routes requests based on a chosen routing strategy. the protocol is structured around assigning domains and roles to models, where requests sent by consumer applications like Pi have task types to enrich routing metadata and thereby accuracy. you ca

dog puppy GIF by DramaFever

Moving Pictures Hello GIF

Jack Nicholson Yes GIF

Make It Rain Money GIF

Black And White Love GIF

Parks And Recreation Mondays GIF

Will Ferrell Reaction GIF

Cat Remember GIF

I Love You Bunny GIF

Make It Rain Money GIF

napoleon dynamite yes GIF

Dance Cat GIF

Show HN: DeepSeek Flash inverted the economics of agent products

There is an adversarial relationship between developers and big model labs.Model labs charged developers higher API prices to subsidize their own agent harness offerings. Think Anthropic charging 5x higher Claude API prices to subsidize consumer subscriptions. So Cursor in a way was subsidizing their own direct competitor.DeepSeek V4 Flash totally inverted this relationship. Now you have a model that beats even Sonnet in some benchmarks and is totally opensourced. Now inference providers are rac

Ask HN: Options for an independent AI researcher with strong results?

I'm outside the AI industry, outside of academia, and no easy contacts into relevant areas. My background lends itself to exploring AI & reasonable level of care checking results. I was focusing on building practical useful things for a portfolio to help change industries mid-career, but that has become something a little different now.The exploration has led to an analytical framework that appears useful more broadly for looking at neural representational models. (It's not a model