The website is filled with popups and looks ugly IMO

No benchmarks shown so claim "the fastest" looks weird

No actual *browser* competitors listed e.g. https://lightpanda.io/

I saw like 20 tools of this kind and there is a new one coming every month. Cursor had something like this at some point. They've removed it

Referencing other sessions is a cool idea tho

> Cursor had something like this at some point. They've removed it.

No, they say that they have removed it, but they haven't. Cursor claims they retired local indexing in favor of something they call "instant grep," which, according to their own support, doesn't use a local index, and they removed the tool in Cursor settings to rebuild the index.

But Cursor still uses a local index. They have just hidden it as a subfolder in your ".git" folder. "~/.git/cursor".

Their hidden index often goes stale, and I had to nuke that folder every time I changed many files. This isn't new; when they officially had a local index, it was often stale too. I developed a script that ran on a daily schedule, every few hours, to alert me when Cursor's index went stale.

I constantly had to watch for Cursor suddenly not finding documents that clearly existed, and it often worked on outdated content. Disabling instant grep removes the hidden index, btw and problem gone.

Hah yes. Ill throw my own into the ring too https://github.com/boyter/cs although its a lot older than most other tools having been started 7 years ago.

Cursor was an interesting case where they were maintaining an index. I think everyone has converged on not doing that, which is where I started, with BM25 with some tweaks on top.

Notable link related to this https://www.youtube.com/watch?v=ZnmtJKFonLk where Jo Kristian Bergum (notable in the search space) agrees with BM25 being a good approach for agentic workflows.

> Cursor had something like this at some point. They've removed it

Any insight into why would be much appreciated because those insights might hold the key to whether this is a usable, sustainable idea to begin with.

I think a lot of people claim it is because in practice letting the AI just use grep yielded better results.

> Referencing other sessions is a cool idea tho

Something something if you're not already doing this you're behind.

I have a skill named read-opencode-db that's literally a 5 line md file as a simple documentation for a python script that allows agent to read other sessions

It's meant for me to reference session ID's directly to look at another agent review results for example

But I don't think that my workflow is well suited for allowing agents to freely grep the database for facts or decisions, I prefer Matt Pocock's domain modelling skill that bakes decisions into versioned and commitable markdown files

In the comments it reads like bonsei falls apart on longer running tasks.

Not really. The largest IQ4_XS quant here is still worth it because Bonsai doesn't offer larger quants. They could beat it if they made a quaternary variant though, I don't know why they're stopping at ternary.

I wonder the same thing for Bonsai 2. ByteShape offers 5 models from IQ2_XXS-2.56bpw (8.8GB), IQ3_XXS-2.88bpw (9.9GB), IQ3_XS-3.01bpw (10.4GB), IQ3_S-3.23bpw (11.0GB) to IQ4_XS-3.84bpw (13.1GB). Their benchmarks show gradual improvement with size and users can pick one to fit theirs need. Bonsai-2-27B now is about 8.6GB. It might be good to have a quaternary version around 10-11GB to fit a computer with 16-24GB RAM.

Agree here, as it is ByteShape wins practicality wise if the goal is doing actual work with these quants!

prismml's title is very misleading. in their own paper the model is at 75% of coding scores.

As said in the article, all of the providers run different runtimes with proprietary, sometimes untested and weird optimisations

There are multiple types of quantisation: weights and KV Cache. Quantizing kv cache can drastically hurt performance

Disclaimer: I'm using reduced motion on my phone, please acknowledge this bias before reading my comment

All of those, citing the pricing page, "websites people remember" look the same and use the same handful of effects

- Fade in on scroll - Big letters - Punishment of firefox users - Fullscreen imagery - Cursor replacement - Annoying takeover of browser scrolling

Of course you would be impressed if you see something like this the first time. If every third company has websites like this, it gets annoying. I don't remember any of them

They look cool on twitter, how they perform independently of it?

I miss "boring" landings. Pretty ones, not wordpress or wix slop, not "beautiful, that's hard to forget. Make no mistakes" ahem...

Look at https://vercel.com/ , https://linear.app/ , https://notion.com , https://apple.com . They're simple, easy to quickly parse, don't take over your browser's decade old predictable patterns

They're pretty. But simple.

Because there is no single "default instance that is always a good choice and wouldn't go down randomly because of lack of funding". That's both a strong and a weak side of fedi

mastodon.social has been around for a decade now, seems stable enough.

I found the opencode fork repo, but no plugin seems available so far

https://github.com/Vibecodelicious/opencode

I think Forgejo is great. But we need to remember the fact that many enterprises pick GitHub or GitLab because they provide paid support and SLA. Also Forgejo Actions are still in beta, while GitLab and GitHub are pretty established solutions for CI/CD

Sourcehut is basically a really barebones web interface for git server, so I don't think it's really comparable to GitHub

For hosting your own projects that's sometimes not a viable solution either. Limiting your open source project to platform other than GitHub hurts it's discoverability, because usually GitHub is what most devs and non devs associate with open source. I heard a lot of "It's not open source if it's not on GitHub". You can mirror your project to GH of course

"Just migrate to X because it's faster" doesn't work that well in the real world

I'm surprised this article is not taken down. OSM wiki states that what3words the company have a good history of taking down code (and maybe articles) like this one, because algorithm (any algorithm that converts any number of words to coordinates) is patented to them in multiple countries

https://wiki.openstreetmap.org/wiki/What3words

The author, if I remember correctly from twitter, was a thorn in the side of the people who developed this system for quite some time. Given his profession I expect he made sure he was on the right side of the law before publishing this.

I think that the example in the article is not a good usecase for this technology. It would be better, cheaper and less error prone to have prebuilt forms that LLM can call like tools, at least for things like changing shipping address

Shipping forms usually need verification of addresses, sometimes they even include a map

Especially if on the other end data that would be inputted in this form, would be stored in the traditional DB

Much better usecase would be use it in something, that is dynamic by nature. For example, advanced prompt generator for image generation models (sliders for size of objects in a scene; dropdown menus with variants of backgrounds or style, instead of usual lists)

You make a good point! There are many common input configurations that will come up again and again, as forms and other types on input (like maps as you mentioned). How can we solve for that?

Maybe a solution would look like the server expression a more general intent -- "shipping address", and leaving it to the client to determine the best UI component for capturing that information. Then the server will need to do its own validation of the user's input, perhaps asking for confirmation that it understood correctly.