Viewing profile — Bnjoroge

As someone who’s building a github actions control plane replacement, the scheduler is extremely simple. It basically the kost naive version of a FiFO queue.

Is it? Last time I checked, I had to maintain a custom fork because they didnt support device auth for remote env so you couldn’t really use your chatGPT sub.

gotcha. yea ideally you take a full live snapshot of my current state, untracked files, processes etc, and resume them in the cloud. Congrats on the launch! A mobile app would also…

Huh? V4Flash is still incredibly price competitive. The new version is right around GLM 5.2 and maybe slightly worse than opus 4.8 depending on which benchmark you use while being …

Kimi’s policy is extreme reasonable.

What’s the experience like going from an active on-going thread to a cloud-hosted one? I dont wanna always work on the cloud, and want my current setup to be exactly the same as in…

I like using exe but I’m not sure what to feel about this if exe itself isnt open source. Granted, their agent is OSS, but still feels somewhat ironic

how's this different from iroh?

certainly sounded like one of

What model is “AI”?

til, thanks!

Using tokens to evaluate models is an outdated approach. Cost per task is what matters. Not all tokens are created equal

Why a clone over a worktree? The obvious disadvantage I can see is you dont share your git objects with a clone and for really large repos that becomes an issue

Demo looks cool, congrats on the ship! Probably missed but is it possible to externally share/view the built artifact outside of prized?

i'll take that 100% over llm slop.

what exactly do they do to "tune" it? It's not Deepseek's official harness, and going direct with deepseek using ur own harness is stupid cheap

I use these guys. https://crof.ai/tos . Their prices match deepseek, pretty dang fast, and support ZDR. Maybe they serve quantized models but I havent seen a drop in quality from m…

It’s a pretty safe assumption that most recent projects use AI in some capacity. Models have gotten pretty good

Did you try Headscale? https://github.com/juanfont/headscale or netbird? The latter has been great for me.

I’ll take that over something AI generated that’s not free

Yea I cant convince myself to pay api pricing unless my employer is doing it

I’ve unfortunately had to temper my excitement with Cognition’s models/products given the amount of unwarranted hype they created with Devin on first release, but hopefully this is…

Hey folks. While running multiple agents and git worktrees with a Docker Compose setup, I kept running into host port, container name, and volume collisions. Before building this t…

Interesting, any benchmarks for how well it works?

Looks cool, but I couldnt find any benchmarks for how well this does. Any links?