cschneid · HackerTrans

2 माह पहलेdiscuss

Odd lots podcast had an interesting snippet about an financial institution that uses AI to make loan decisions. The guest said that they only use it on applicants who were rejected in the traditional sequence, and then uses AI to accept them if possible. That way there's an articulable reason for a rejection, but they use the non-deterministic AI to allow an extra person through - since the laws about loans are mostly around not discriminating against people - companies are (generally) welcome to accept whoever.

cschneid

5 माह पहलेdiscuss

Can this take vague ideas, do iterative design with me, and breakdown tasks to then pass off to agents to build?

I was playing with a very similar project recently that was more focused on a high level input ("Build a new whatever dashboard, <more braindump>") and went back and forth with an agent to clarify and refine. Then broke down into Epics/Stories/Tasks, and then handed those off automatically to build.

The workflow then is iterating on those high level requests. Heavily inspired by the dark factory posts that have been making the rounds recently.

From a glance, it seems like this is designed so that I write all the tasks myself? Does it have any sort of coordination layer to manage git, or otherwise keep agents from stepping on each other?

cschneid

5 माह पहलेdiscuss

I have been using Superset (https://superset.sh/) and it has worked really well to automate creating & deleting worktrees, with their own terminals, and keeping everything organized. Great for running work in parallel.

It's really just a terminal emulator w/ a bunch of extra helpers to make coding agents work well. Which I really like since it doesn't try to wrap claude or codex in it's own ui or anything tricky.

cschneid

6 माह पहलेdiscuss

I agree, I have 'written' a handful of rubocop rules that are hyper specific to the codebase I work on. I never would have bothered before claude code. Stuff like using out custom logger correctly, or to not use Rails.env because we have our own (weird of course) env system.

cschneid

8 माह पहलेdiscuss

so apparently they have custom hardware that is basically absolutely gigantic chips - across the scale of a whole wafer at a time. Presumably they keep the entire model right on chip, in effectively L3 cache or whatever. So the memory bandwidth is absurdly fast, allowing very fast inference.

It's more expensive to get the same raw compute as a cluster of nvidia chips, but they don't have the same peak throughput.

As far as price as a coder, I am giving a month of the $50 plan a shot. I haven't figured out how to adapt my workflow yet to faster speeds (also learning and setting up opencode).

cschneid

8 माह पहलेdiscuss

Yes this is the output speed. Code just flashes onto the page, it's pretty impressive.

They've claimed repeatedly in their discord that they don't quantize models.

The speed of things does change how you interact with it I think. I had this new GLM model hooked up to opencode as the harness with their $50/mo subscription plan. It was seriously fast to answer questions, although there are still big pauses in workflow when the per-minute request cap is hit.

I got a meaningful refactor done, maybe a touch faster than I would have in claude code + sonnet? But my human interaction with it felt like the slow part.

cschneid

7 वर्ष पहलेdiscuss

I use AutoSleep on Apple Watch 4. It is good at poking me after a few days of not sleeping enough with a message like: "You slept for 5:38 last night, and have a sleep debt of 12%". That's enough of a poke to get my sleep back on track.

I've also used it to experiment a bit with how drinking at night affects my sleep. (noticeably!). I could do that with just how I feel, but the hard data is easier to correlate later.

comments