tinodb
tinodb on Hacker News
Do you pay for everything in package.json or pyproject.toml (or <packagemanagerX>)?
I dove into the scoring a bit and must say that there are quite some overly subjective rules in the Verbosity set. Also some that go against pep8. This sounds like trying to make the llm pass an exam without telling it it will fail if it uses a blue pen…
I’m rerunning some now without those rules.
And also, couldn’t we greatly improve the outcome if we give the llm those quality gates? That is more interesting to me.
It certainly does. You need to weigh the users privacy with your interests and can’t just put them aside. Noncompliance leads to quite large fines. You can easily find examples of fines given.
The DPA’s are short on capacity, sure, and large corps will try to fight the fines in court. But to describe it as “just hoops whilst allowing everything” is unfair.
Commit them in the root of your monorepo :P
Or create a repo for skills and have people check those out in their user skills dir.
Or in case of Claude, create a plugin that your people install.
> 3. Actions
It is somewhat explained as a convention or something built-in, but I can't find much about it elsewhere. Is it the author's own convention or am I missing something?
Which design ideas are those? (Asking out of curiosity, happy pi user here!)
Can you just stop the spam?
But in general you are one of the few that does. Many devs do find git rebases scary. Having done it in both I can say with JJ it is much much simpler (especially with jjui).
I use codex through the pi agent. It’s wonderful and easy to create whatever extension or hook you want!
I’d use it with Claude too if they hadn’t banned it…
So now you know how much it matter :)
Do you consider the implementation of such specs by another human to (always) be correct and deterministic?
Heck, if I reimplement something I worked on a month ago it’s probably not going to be the exact same. Being non deterministic needn’t to be a problem, as long as it falls within certain boundaries and produces working results.
Given Viktor’s helpfulness here, I can’t help but wonder how it would respond to: “please create a backup of the C-Team and HR channels”…
ITs worst nightmare no?
It certainly isn’t. It is more a way of discovery on how to implement something, with the benefit of being able to safely (and thus easily) change it later.
The 99 Bottles book by Sandi Metz [0] is a good short display of how it works and where it helps actually building maintainable software
[0] https://sandimetz.com/99bottles
I have found that with a good plan we are able to make big refactors quite a bit faster. The approach is that our /create-plan command starts high level, and only when we agree on that, fills in the details. It will also determine in what pull requests it plans to deliver it. The size estimation of the prs is never correct, but it gives a good enough phase split for the next step. Which is letting it rip with a “Ralph loop” (just a bash script while with claude -p —yolo). This with instructions to use jj (or git) and some other must read skills.
This lets us review the end result, and correct with a review. That then gets incorporated whilst having claude rework the actual small prs that we can easily review and touch up.
I must say jj helps massively in staying sane and rebasing a lot. Claude fixes the conflicts fine.
We have been able to push ~5K of changes in a couple days, whilst reviewing all code, and making sure it’s on par with our quality requirements. And not writing a line of code ourselves.
I would have never attempted these large scale refactors, and we would have been stuck with the tech debt forever in the past.
Thanks for creating Ghostty! Is there a chance to have shorter release cycles? I switched to nightly because of the mem bug and search, but ideally would like to be on a more stable channel.
Nice, I had the same idea for a enforced TDD state machine! I wouldn’t tie it to all the other stuff though, but I might try it out.
For upgrading frameworks and such there are usually not that many architectural decisions to be made, where you care about how exactly something is implemented. Here the OP could probably verify the build works, with all the expected artifacts quite easily.
Slow_er_. For all programs talked about in this thread it is fast enough. Especially if you don’t need to host it at Microsoft/Google scale.
docs.sprites.dev requires authentication? And what about adding /llm.txt? I want Claude Code Web to install the cli and deploy what it is working on in a sprite :)
Not if you want to run multiple agents in parallel…
Codex is even better in my experience at reviewing. You can find the prompt it uses in the repo
How do you deal with one of transactions? How do you assign them to the right account?
Yet, you add another attack vector, something that is very willing to do stuff, as long as you prompt it right…
As Simon Wilison clearly laid out, 99% secure isn’t secure and you think you can fix it by adding mor/better prompts?
Which methods do you have planned outside of “better prompting/fine tuning”?
Scaleway and OVH offer all the basics and more (kubernetes, networking, hosted dbs, queues, storage, GPUs etc). It’s google workspace/microsoft 365 that has no equivalent.
Because they don’t offer every service AWS offers? They offer plenty of hosted databases, queues and what not that it shouldn’t be too hard to move things over. Especially not if you are on Kubernetes. Not if you are all in on lambdas of course but that is a problem in and of itself.
Yes, this would make us programmers so happy wouldn’t it :)
I don’t agree with the given answer to “Why the PO wants you to estimate”. The author cites external reasons (made commitments etc) that shouldn’t have been there in the first place.
Sure, in some lines of software development you really have a “deadline”, if you are working towards some event or launch date. But most of the time estimates are needed to determine *if it is worth it*. Can it be built in 2 weeks, let’s go. Is it gonna cost 2 months, then let’s prioritise something else. That isn’t to say you always have to go with the shortest te build features (you can apply "CD3" – Cost of Delay Divided by Duration), but you need it to compare alternatives.
For lots of jobs of “text querying” they do good enough of a job to be on par with humans (which are not infallible either).
And there are applications where you don’t have/wouldn’t pay another human, and the job that an AI does for mere cents is good enough most of the times. Like doing an analysis on a legacy codebase. I’ll read and verify, but running that “query” then saved me a lot of time.
Not everything needs to be deterministic to be of value.