Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

simonwillison.net

Post reply on HN
Print view View original

11–20 of 93 posts

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#11

Post by andy_ppp »

Tiberium wrote: post #2

The title cost is only if this was raw API usage, but it was included in a subscription, so it's a small subset of the $200 plan: > I upgraded to the Claude Max $200/month plan (I was previously on $100/month) to increase my Fable allowance for the remaining time until the July 7th Fablepocalypse, when even Claude Max subscribers will have to pay full API cost for the model. I really wonder if Anthropic will stick wi…

This is to prevent Chinese labs distilling Claude again right? And free advertising again?

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#12

Post by embedding-shape »

dreadnip wrote: post #3

The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model wi…

> There is never a “Nothing found, good to go!”.

Like when you do recursive programming, have you tried providing more/better stop conditions? If you literally just say "Continue until there are no more issues" then it'll do just that, but if you scope it better, like "Only mention issues related to X, Y or that leads to Z" and so on, you'll get less noise and more focus on issues that actually matter (to you).

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#13

Post by MallocVoidstar »

baq wrote: post #8
dreadnip wrote: post #3

The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model wi…

You didn’t do it enough. They stop finding bugs eventually. Also, different models can find different bugs (though they do find the same ones, too, which is good and expected). For best results you want to run multi model reviews in loops. If you had multiple people look at your PRs multiple times on different days results would be very similar.

No, depending on the complexity of the issue models can be into loops, where they go "this is definitely an issue and must be fixed", and then the resulting fixed code gets "this is definitely an issue and must be fixed", and then the resulting fixed code has the original 'issue'.

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#14

Post by embedding-shape »

nvme0n1p1 wrote: post #9
threatripper wrote: post #4

Earlier quoted context omitted.

You get the same result if you pay humans a good sum of money to find issues.

Definitely not. I've never seen a human trapped in that kind of infinite loop. Humans know that if they don't stop at the end of the day, they don't get to go home to their wife, and if they don't finalize their list of issues, they never get their contract paid out.

Pay people per hour of work and even if there is no actual work, people will definitively find a way of spending hours doing things. If you've worked with contractors/outsourced roles before this will happen from time to time.

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#15

Post by embedding-shape »

Tiberium wrote: post #2

The title cost is only if this was raw API usage, but it was included in a subscription, so it's a small subset of the $200 plan: > I upgraded to the Claude Max $200/month plan (I was previously on $100/month) to increase my Fable allowance for the remaining time until the July 7th Fablepocalypse, when even Claude Max subscribers will have to pay full API cost for the model. I really wonder if Anthropic will stick wi…

> especially in the light of GPT 5.6 very likely coming out next week

Finally have an explanation why GPT 5.5 xhigh felt dumber and dumber these last few weeks, always the same thing when a new model release is about to come out...

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#16

Post by onion2k »

dreadnip wrote: post #3

The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model wi…

If I keep running the same prompt, it will keep finding issues.

I've had the same experience, but whenever I've reviewed what it finds it's basically right. It's pedantic, and a lot of the problems aren't things I really care about, but they definitely are real problems.

I'm not sure you can blame the AI for always finding problems if a) you asked it to, and b) there are problems to find.

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#17

Post by starquake »

dreadnip wrote: post #3

The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model wi…

I use Claude Code and one of the steps in my workflow is do a review loop until no issues are found and it never loops. So my experience is entirely different. Even if I say: fix all issues. So not only the critical issues.

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#18

Post by toxik »

embedding-shape wrote: post #15
Tiberium wrote: post #2

The title cost is only if this was raw API usage, but it was included in a subscription, so it's a small subset of the $200 plan: > I upgraded to the Claude Max $200/month plan (I was previously on $100/month) to increase my Fable allowance for the remaining time until the July 7th Fablepocalypse, when even Claude Max subscribers will have to pay full API cost for the model. I really wonder if Anthropic will stick wi…

> especially in the light of GPT 5.6 very likely coming out next week Finally have an explanation why GPT 5.5 xhigh felt dumber and dumber these last few weeks, always the same thing when a new model release is about to come out...

Opus has been extremely stupid recently, reckon that's because Fable needs to look appealing?

Re: sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

#20

Post by Myzel394 »

dreadnip wrote: post #3

The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model wi…

That's just plain wrong. The new models do not hallucinate as much as they used to (in my personal experience)
Post reply on HN