Viewing profile — RussianCow
RussianCow
HN member- Joined
- Sun, May 26, 2013, 1:07 AM UTC
- HN karma
- 4,114
- Public activity
- 1,593 items
- HN profile
- View on Hacker News ↗
About RussianCow
My current venture is Semi-Decent, a software consultancy that helps businesses build and scale software products. We are intensely pragmatic and focus on combining lean MVPs with user research to guide our clients towards growth. We take the risk out of software projects by keeping scope short and focused and offering a money-back guarantee. https://www.semi-decent.com/
I also run a side business making bespoke, sustainable craft cocktails for events: https://www.theminimalmixologist.com/
Please get in touch! I'd love to chat.
sasha+hn@chedygov.com
Recent public activity
-
comment
Comment #49214433
Someone brings this up on just about every AI-related thread. I think it's nonsense. Nobody wants to maintain a fork of any remotely complex software, not even with AI. And in a co…
-
comment
Comment #49203651
That likely isn't as relevant for on-device iPhone usage as it is for Real Work™. I won't notice the difference between 50tps and 1000tps when asking Siri a question.
-
comment
Comment #49187368
There's no reason you couldn't present a GUI over an SSH connection. Whether the agent is running locally or remotely is orthogonal to the type of interface used.
-
comment
Comment #49146468
I'm not confusing anything since you can't use custom harnesses with your Claude subscription—you have to use Claude Code. So as far as the Claude sub is concerned, the models and …
-
comment
Comment #49137325
They're not as good. I've tried all the options available a couple months ago, and none of them feel nearly as polished as Cursor. For one thing, Cursor Tab is just far better than…
-
comment
Comment #49137105
> the results are much better than clowning on bloated CC. I won't argue with the cost effectiveness, but the results are very much not better. Opus and Fable are in a different le…
-
comment
Comment #49049925
The problem is that companies tend to exaggerate their own scale and think they need k8s and dedicated infra people when they could get by with a handful of beefy VMs or dedicated …
-
comment
Comment #49049912
I haven't used them but aren't they basically modernized Heroku? What's different?
-
comment
Comment #48983533
This seems like an arbitrary line to draw. Should your photo viewing software also not provide editing tools? If it's useful, why not?
-
comment
Comment #48928857
It depends. For something high stakes or inherently complex, sure, you don't want to have to clean up the agent's mess afterwards. But for many tasks like building web UIs, the dif…
-
comment
Comment #48925173
Once you've used a model that runs at hundreds of TPS, it's hard to go back. Everything completes so quickly that you can iterate without breaking out of flow state. My biggest gri…
-
comment
Comment #48909196
The system prompt and available tools would likely only change for different agent types. So how they're launched probably doesn't matter. I say this as I don't actually know how C…
-
comment
Comment #48894189
Yes, Codex has its own sandbox which you can disable: https://learn.chatgpt.com/docs/sandboxing?surface=app Cursor has something similar. I don't know about Claude Code but I assum…
-
comment
Comment #48887058
Compared to the primary agent, maybe. But it's highly unlikely that all the agents have different tools and system prompts than each other, and those account for the bulk of the co…
-
comment
Comment #48840864
You cannot; you must use either their Devin Desktop app or the Devin CLI.
-
comment
Comment #48839881
But they don't appear to subsidize them to the same degree. I've only been using Devin for less than a month, but I've been hitting the limits of the $20/month plan way more quickl…
-
comment
Comment #48838434
But that 10% is the most important part! Getting the plumbing wrong means you might have bugs or your code is brittle. Getting the domain-specific business logic wrong means your p…
-
comment
Comment #48837314
Ironically, Devin Desktop is one of those tools. It supports any harness that supports ACP (which is most of them)—you can use Claude Code, Codex, OpenCode, etc from the Devin Desk…
-
comment
Comment #48837252
But some requirements you don't realize you have until you start building. With a fast model, you can surface those really quickly and have more time to iterate and explore differe…
-
comment
Comment #48837059
The regular one (not the fast variant) is free but slow. The "Lightning" variant (which uses Cerebras and gets supposedly 1000 TPS) costs $12.50/M output, $2.5/M input, $1/M cached…
-
comment
Comment #48836986
The "Lightning" (Cerebras) variant isn't free, only the regular one, which runs closer to 50 TPS in my experience with SWE 1.6.
-
comment
Comment #48805583
That's not why Elm is an ideal language for LLMs: it's because, if it compiles, it's most likely working software. Agentic workflows have gotten significantly better over the last …
-
comment
Comment #48795646
> asking an LLM to reverse engineer and make your own plugin is trivial. If you already have engineers on staff, a few tens (or even hundreds) of dollars per month per plugin is li…
-
comment
Comment #48764834
At least 3 times a month. I have a rental property and my tenant prefers to mail a check instead of paying extra to pay electronically. My spouse gets paid by check for dumb reason…
-
comment
Comment #48763308
> Also why do you need bank app on your phone? Many banks gate features like mobile check deposit behind the native app. The nearest ATM is 20 minutes away from my house, so unfort…