Hacker Newsnew | past | comments | ask | show | jobs | submit | moozilla's commentslogin

> Fable works extremely well to drive Sol as a subagent.

Curious what method you like for doing this? I've tried a few options and I haven't found one I'm happy with yet.


I'm using a slimmed down version of this skill:

https://github.com/steipete/agent-scripts/blob/main/skills/c...

The important bit I found is to explicitly remind Claude that Sol 5.6 is a very smart and good model; otherwise, Claude performs its normal condescension towards any non-Claude model behavior and insists on reading all the diffs in full and testing all of Sol's work, negating any token savings.


This is only true for poor quality coffee. The hot temperature masks defects (bitterness). Good coffee tastes better as it cools. https://www.baristamagazine.com/the-temperature-paradox-why-...


Even that article carries on about the experience of having the coffee hot, eg

"This doesn’t mean drinking room-temperature coffee exclusively. The complete experience encompasses the entire temperature journey." and "High temperatures deliver immediate aromatic impact—the unique, irreplaceable value of fresh coffee."

I'm also not sure bitterness should be considered a defect in coffee, it's part of the flavor profile and actually peaks in perception at a higher temperature according to that article.


I find this is definitely true for americano and pour overs but I don't drink enough espresso to know if this also true? I at least feel the sentiment that you want to drink an espresso fairly quickly although I do enjoy savouring it and also drink water in between to re-experience it on the palette


> I at least feel the sentiment that you want to drink an espresso fairly quickly although

There is so many different ways and subjective taste palettes that I don't think there is one way. When I was younger and in a rush, I always drank my espresso maybe 30-60 seconds after they made it, the heat became part of what I enjoyed (eventually). Now I let it cool down to just above room-temperature if I know the place has good beans/roast as I feel even more flavor then. If I'm drinking a Americano, then it pretty much ends up room temperature before I even start drinking it.

Then we have my neighbor who I end up at the same cafe in sometimes, who poor their espresso into a glass of ice, then drink it, and they seem to enjoy their coffee just as much as me, so in the end, I don't think there is a right way here :)


Midjourney is not VC backed. They have a bit about this in the article:

> As a reminder, Midjourney has no investors. We are a totally new kind of research lab. We've seen academic, corporate, and government labs - but we are a distinct (and curious) new thing: we are a community-backed research lab.


Yeah sure. That's not going to be a sustainable model. Once the tech is available and money is to be made, lots of for-profit alternatives will appear with marketing and lobby budgets that will take over the market.

Remember Open AI was a non-profit at some point. Look at how that turned out.


I know the founder through a lot of light discussion. If lots of for-profit alternatives become serious competition, he'd rather move on to something else than take on VC money. His POV is that he already has more money than he ever wanted. All he wants now is to do fun research.


Exactly. With "you" in the original post I didn't mean the exact actor right now but whoever will be in charge eventually. When good actors leave the stage, you are only left with the bad ones.


Last time I tried home row mods I could not get over how bad it felt having the letter not appear until I lifted the key rather than immediately on the keypress. Am I just overly sensative or is this just something you get used to over time?


I had a much better experience shifting them down a row so they’re “bottom row mods”, since those keys (if using QWERTY) are much less frequently used.

There’s also features like chordal hold and flow tap which have improved the home/bottom row mod behaviour.


I also found this bit funny:

> We also suspect that the geographical and cultural factors may have influenced interaction patterns, given that all our participants were residing in Türkiye.


You could go with the title from the associated YouTube video (https://www.youtube.com/watch?v=lXUZvyajciY)?

Andrej Karpathy — “We’re summoning ghosts, not building animals”


It's a good suggestion, but where the 'autocomplete' quote is scoped too narrowly, this one is maybe scoped too broadly. Neither really represent what the article is about.


I like to think of models leaving "useless comments" as a way to externalize their reasoning process - maybe they are useless at the end, but leaving them in on a feature branch seems to marginally improve future work (even across conversations). I currently leave them in and either manually clean them up myself before putting up a PR for my team to review or run a final step with some instructions like "review the diff, remove any useless comments". Funnily enough Claude seems pretty competent at identifying and cleaning up useless comments after the fact, which I feel like sort of proves my hypothesis.

I've considered just leaving the comments in, considering maybe they provide some value to future LLMs working in the codebase, but the extra human overhead in dealing with them doesn't seem worth it.


I've been wondering if the "you're absolutely right!" thing is also similar. Like maybe it helps align Claude with the user or something, less likely to stray off or outright refuse a task.


If anyone is curious on the context:

https://x.com/thdxr/status/1933561254481666466 https://x.com/meowgorithm/status/1933593074820891062 https://www.youtube.com/watch?v=qCJBbVJ_wP0

Gemini summary of the above:

- Kujtim Hoxha creates a project named TermAI using open-source libraries from the company Charm.

- Two other developers, Dax (a well-known internet personality and developer) and Adam (a developer and co-founder of Chef, known for his work on open-source and developer tools), join the project.

- They rebrand it to OpenCode, with Dax buying the domain and both heavily promoting it and improving the UI/UX.

- The project rapidly gains popularity and GitHub stars, largely due to Dax and Adam's influence and contributions.

- Charm, the company behind the original libraries, offers Kujtim a full-time role to continue working on the project, effectively acqui-hiring him.

- Kujtim accepts the offer. As the original owner of the GitHub repository, he moves the project and its stars to Charm's organization. Dax and Adam object, not wanting the community project to be owned by a VC-backed company.

- Allegations surface that Charm rewrote git history to remove Dax's commits, banned Adam from the repo, and deleted comments that were critical of the move.

- Dax and Adam, who own the opencode.ai domain and claim ownership of the brand they created, fork the original repo and launch their own version under the OpenCode name.

- For a time, two competing projects named OpenCode exist, causing significant community confusion.

- Following the public backlash, Charm eventually renames its version to Crush, ceding the OpenCode name to the project now maintained by Dax and Adam.


This is like game of thrones, dev edition. Thanks for the background.

/me up and continues search for good people and good projects.


Oh wrong Adam, our Adam cofounded Statmuse https://x.com/adamdotdev


Quick correction, from what I understand Dax and Adam started from scratch for the new version.


I'm surprised this doesn't get brought up more often, but I think the main explanation for the divide is simple: current LLMs are only good at programming in the most popular programming languages. Every time I see this brought up in the HN comments section and people are asked what they are actually working on that the LLM is not able to help with, inevitably it's using a (relatively) less popular language like Rust or Clojure. The article is good example of this, before clicking I guessed correctly it would be complaining about how LLMs can't program in Rust. (Granted, the point that Cursor uses this as an example on their webpage despite all of this is funny.)

I struggled to find benchmark data to support this hunch, best I could find was [1] which shows a performance of 81% with Python/Typescript vs 62% with Rust, but this fits with my intuition. I primarily code in Python for work and despite trying I didn't get that much use out of LLMs until the Claude 3.6 release, where it suddenly crossed over that invisible threshold and became dramatically more useful. I suspect for devs that are not using Python or JS, LLMs have just not yet crossed this threshold.

[1] https://terhech.de/posts/2025-01-31-llms-vs-programming-lang...


As someone working primarily with Go, JS, HTML and CSS, I can attest to the fact that the choice of language makes no difference.

LLMs will routinely generate code that uses non-existent APIs, and has subtle and not-so-subtle bugs. They will make useless suggestions, often leading me on the wrong path, or going in circles. The worst part is that they do so confidently and reassuringly. I.e. if I give any hint to what I think the issue might be, after spending time reviewing their non-working code, then the answer is almost certainly "You're right! Here's the fix..."—which either turns out to be that I was wrong and that wasn't the issue, or their fix ends up creating new issues. It's a huge waste of my time, which would be better spent by reading documentation and writing the code myself.

I suspect that vibe coding is popular with developers who don't bother reviewing the generated code, either due to inexperience or laziness. They will prompt their way into building something that on the surface does what they want, but will fail spectacularly in any scenario they didn't consider. Not to speak of the amount of security and other issues that would get flagged by an actual code review from an experienced human programmer.


Here's an attempt at cleaning it up with Gemini 2.5 Pro: https://rentry.org/nyznvoy5

I just pasted the YouTube link into AI Studio and gave it this prompt if you want to replicate:

reformat this talk as an article. remove ums/ahs, but do not summarize, the context should be substantively the same. include content from the slides as well if possible.


Pretty good, except it’s not Bismarck but Fontane. ;) Also, I’m comparing myself to CGP Grey, not whatever it’s transcribed. :D


Thanks, saved me so much time


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: