Hacker News: janpaul123https://news.ycombinator.com/user?id=janpaul123Hacker News RSShttps://hnrss.org/hnrss v2.1.1Fri, 26 Jun 2026 22:32:07 +0000<![CDATA[New comment by janpaul123 in "An entire Herculaneum scroll has been read for the first time"]]>And a new $1M Vesuvius Challenge Grand Prize will be announced in coming days: https://www.youtube.com/watch?v=96oTlQm0KBw&t=5405s

]]>Fri, 26 Jun 2026 01:05:21 +0000https://news.ycombinator.com/item?id=48681197janpaul123https://news.ycombinator.com/item?id=48681197https://news.ycombinator.com/item?id=48681197<![CDATA[New $1M Vesuvius Challenge Grand Prize will be announced in coming days]]>Article URL: https://www.youtube.com/watch?v=96oTlQm0KBw

Comments URL: https://news.ycombinator.com/item?id=48681121

Points: 2

# Comments: 0

]]>Fri, 26 Jun 2026 00:51:45 +0000https://www.youtube.com/watch?v=96oTlQm0KBwjanpaul123https://news.ycombinator.com/item?id=48681121https://news.ycombinator.com/item?id=48681121<![CDATA[New comment by janpaul123 in "An entire Herculaneum scroll has been read for the first time"]]>Ex-project lead here. The most incredible part is buried in a 7 hour long video. Last night they also unwrapped 140 columns of new text in the PHerc. Paris. 4 scroll: https://x.com/JanPaul123/status/2070304769273725278

]]>Fri, 26 Jun 2026 00:36:50 +0000https://news.ycombinator.com/item?id=48681019janpaul123https://news.ycombinator.com/item?id=48681019https://news.ycombinator.com/item?id=48681019<![CDATA[New comment by janpaul123 in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"]]>Kilo Code CEO here. This is why open source is so important!!

]]>Sat, 12 Jul 2025 20:34:44 +0000https://news.ycombinator.com/item?id=44544943janpaul123https://news.ycombinator.com/item?id=44544943https://news.ycombinator.com/item?id=44544943<![CDATA[New comment by janpaul123 in "OpenAI’s Windsurf deal is off, and Windsurf’s CEO is going to Google"]]>Kilo Code CEO here. We’d like to welcome ex-Windsurf users by offering you $100 in credits. :D We'd love to show how through open source there is a better way (better community, more transparent pricing, won't mess with your or the product). https://blog.kilocode.ai/p/windsurf-is-over-switch-to-open-s...

]]>Sat, 12 Jul 2025 20:33:53 +0000https://news.ycombinator.com/item?id=44544938janpaul123https://news.ycombinator.com/item?id=44544938https://news.ycombinator.com/item?id=44544938<![CDATA[Cursor's 500 requests => "unlimited" => 225 requests]]>Article URL: https://blog.kilocode.ai/p/cursors-500-requests-unlimited-225

Comments URL: https://news.ycombinator.com/item?id=44474001

Points: 5

# Comments: 0

]]>Sat, 05 Jul 2025 16:59:39 +0000https://blog.kilocode.ai/p/cursors-500-requests-unlimited-225janpaul123https://news.ycombinator.com/item?id=44474001https://news.ycombinator.com/item?id=44474001<![CDATA[New comment by janpaul123 in "Claude 4"]]>At Kilo we're already seeing lots of people trying it out. It's looking very good so far. Gemini 2.5 Pro had been taking over from Claude 3.7 Sonnet, but it looks like there's a new king. The bigger question is how often it's worth the price.

]]>Thu, 22 May 2025 19:59:00 +0000https://news.ycombinator.com/item?id=44066202janpaul123https://news.ycombinator.com/item?id=44066202https://news.ycombinator.com/item?id=44066202<![CDATA[New comment by janpaul123 in "An update to our pricing"]]>Seeing the $ every time I do something, even if it's $0.50, can be a little stressful. We should have an option to hide it per-request and just show a progress bar for the current topup.

]]>Mon, 21 Apr 2025 22:47:57 +0000https://news.ycombinator.com/item?id=43757345janpaul123https://news.ycombinator.com/item?id=43757345https://news.ycombinator.com/item?id=43757345<![CDATA[New comment by janpaul123 in "An update to our pricing"]]>Yeah, my colleague just wrote about this exact problem of incentive misalignment with Cursor and Windsurf https://blog.kilocode.ai/p/why-cursors-flat-fee-pricing-will

The economist in me is says "just show the prices", though the psychologist in me says "that's hella stressful". ;)

]]>Mon, 21 Apr 2025 21:07:25 +0000https://news.ycombinator.com/item?id=43756488janpaul123https://news.ycombinator.com/item?id=43756488https://news.ycombinator.com/item?id=43756488<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>I agree, this would be good to have soon, especially as good models keep getting smaller, and hardware keeps getting cheaper.

]]>Thu, 27 Mar 2025 13:27:42 +0000https://news.ycombinator.com/item?id=43493404janpaul123https://news.ycombinator.com/item?id=43493404https://news.ycombinator.com/item?id=43493404<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>100% agreed on both points. Point 1 relates to https://news.ycombinator.com/item?id=43486526 as well. It's one of the biggest challenges, though maybe it'll automatically get better through models with bigger context windows (we can't assume that though)?

]]>Wed, 26 Mar 2025 21:26:51 +0000https://news.ycombinator.com/item?id=43487521janpaul123https://news.ycombinator.com/item?id=43487521https://news.ycombinator.com/item?id=43487521<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Thanks! That does look like a great tool.

]]>Wed, 26 Mar 2025 21:25:17 +0000https://news.ycombinator.com/item?id=43487492janpaul123https://news.ycombinator.com/item?id=43487492https://news.ycombinator.com/item?id=43487492<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>At this point we plan to monetize enterprise features (LDAP login, things like that).

]]>Wed, 26 Mar 2025 20:21:43 +0000https://news.ycombinator.com/item?id=43486818janpaul123https://news.ycombinator.com/item?id=43486818https://news.ycombinator.com/item?id=43486818<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Still a small percentage! Let's get more of this happening.

]]>Wed, 26 Mar 2025 20:16:58 +0000https://news.ycombinator.com/item?id=43486766janpaul123https://news.ycombinator.com/item?id=43486766https://news.ycombinator.com/item?id=43486766<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Good point! In that sense we're similar to most AI coding agents in that the languages we do well are the languages the mainstream LLMs do well. We might zoom in and add really good support for particular languages though (not decided yet), in which case we'll def mention that front and center!

Have you found any LLMs or coding agents that work well with Haxe? It might be a bit too niche for us (again, not sure yet), but I'd be very curious to see what they do well!

]]>Wed, 26 Mar 2025 20:13:25 +0000https://news.ycombinator.com/item?id=43486706janpaul123https://news.ycombinator.com/item?id=43486706https://news.ycombinator.com/item?id=43486706<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>In roughly the last 2 weeks, yes. It helped that everyone involved also activated their network, so we got a multiplicative effect. Can't speak to funding for now unfortunately.

]]>Wed, 26 Mar 2025 20:05:23 +0000https://news.ycombinator.com/item?id=43486598janpaul123https://news.ycombinator.com/item?id=43486598https://news.ycombinator.com/item?id=43486598<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Yeah, this is a great workflow! What's more, agents are particularly good at writing tests, since they're simpler and mostly linear, so they can even help with that part.

As to your point of automating retries, with my last prototype I played a lot with having agents do multiple parallel implementations, and then pick the first one that works, or lets you choose (or even have another agent choose).

Have you tried any tools that have this workflow down, or at least approach it?

]]>Wed, 26 Mar 2025 20:04:12 +0000https://news.ycombinator.com/item?id=43486576janpaul123https://news.ycombinator.com/item?id=43486576https://news.ycombinator.com/item?id=43486576<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Yes! This is high on our list. Context window compression is a big deal, and this is one of the main ways to do it, IMO.

Have you tried any tools that do this particularly well?

]]>Wed, 26 Mar 2025 20:01:09 +0000https://news.ycombinator.com/item?id=43486526janpaul123https://news.ycombinator.com/item?id=43486526https://news.ycombinator.com/item?id=43486526<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>Totally agree!

]]>Wed, 26 Mar 2025 18:37:14 +0000https://news.ycombinator.com/item?id=43485362janpaul123https://news.ycombinator.com/item?id=43485362https://news.ycombinator.com/item?id=43485362<![CDATA[New comment by janpaul123 in "Kilo Code: Speedrunning open source coding AI"]]>We’ll take all the features people love in other products, and implement them in a coherent package as quickly as we can.

]]>Wed, 26 Mar 2025 18:33:59 +0000https://news.ycombinator.com/item?id=43485322janpaul123https://news.ycombinator.com/item?id=43485322https://news.ycombinator.com/item?id=43485322