Viewing profile — jumploops

[dead]

I recently spun up a simple app for our annual mango tasting event[0] using Cloudflare Workers and Durable Objects. It worked really well! Excited to see more options outside of Cl…

Contrary to the title and intro, this appears to be an agentic _workflow_ builder/runner, not an advanced “agent harness” A few things: - they note: “nothing in this post proves it…

> By the time I was ready to build a keeper, I had accumulated a scar-tissue document that was empirically sufficient to guide an agent through most of the important decisions, at …

The models are commodities. Valuations, however, are being built on the models themselves as the product.

Reminder, this is in the context of "dumb human" prompting. The task is to build a MIPS interpreter to run Doom. The "failed" workflow decided that it couldn't prove Doom was booti…

I’ve thrown my agentic workflow at Terminal Bench 2.1 and it found a bunch of issues (aka failed tests) because the prompts are “bad” and verifiers are overly specific. As an examp…

All of the benchmarks are pretty terrible when you look under the hood. For context, I've been iterating on a "supervisor" to replace a lot of the rigamarole spent when working wit…

My preschooler loves the Untitled Goose Game, please vibe-port this to the Switch (:

Indoor air quality improvements were one of my “pandemic sourdough” activities. After testing a variety of AQI sensors, I ended up acquiring multiple Airthings-branded devices. The…

We’re in the process of open-sourcing a few sub-projects within a monorepo, and didn’t know this existed! I’m curious what downsides folks have experienced with this tool? Any tips…

I don't disagree, we've seen performance shift with capacity changes in the past. With that said, I doubt OpenAI would choose to publish a singular coding benchmark for a new model…

Don't appreciate the slander, but I'll respond anyhow. Contrary to your predisposition, we're actually quite peeved that we might be seeing results from 5.6 instead of 5.5, as it's…

[dead]

If you used GPT-5.5 over the last 24 hours or so, you may have already had access to 5.6. I've been running some tests on a harness we're building, and suddenly saw a jump in a few…

As an American with mostly Western European ancestors (according to a popular DNA testing site), I've always considered Romans as some distant/tangentially related group. It was su…

I've been quite impressed with DeepSeek v4 Flash running via antirez's ds4[0]. It feels like a GPT-4 class model in terms of "stored knowledge" but is better at long-horizon tool c…

> the conversation that generates the code is becoming the true source of our software This is close, but not quite spot on. I've found that I'll test more ideas _with code_ using …

This is neat! I love that your Step 15 shows an accurate version of the 3d helix, rather than the highly-viral "vortex" animation from a few years back[0] It'd be awesome to scale …

It's interesting that we're seeing these gains when it seems Mythos/Fable is "just" a scaled up version of their existing architecture[0]. When GPT 4.5 launched, the gains compared…

No connection, just found it posted elsewhere and thought it was interesting!