2026/06/30

Newest at the top

2026-06-30 22:07:10 +0000troydm(~troydm@user/troydm) troydm
2026-06-30 22:01:58 +0000sp1ff(~user@2601:1c2:4080:14c0:5df2:f2f4:8a07:70ec) sp1ff
2026-06-30 21:58:45 +0000rin(~user@2001:1c00:a16:9d00:461a:c09a:1fd6:97a1) (Client Quit)
2026-06-30 21:57:09 +0000rin(~user@2001:1c00:a16:9d00:461a:c09a:1fd6:97a1)
2026-06-30 21:56:34 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 249 seconds)
2026-06-30 21:55:40 +0000sp1ff(~user@2601:1c2:4080:14c0:5df2:f2f4:8a07:70ec) (Remote host closed the connection)
2026-06-30 21:53:35 +0000schuelermine(~Thunderbi@user/schuelermine) schuelermine
2026-06-30 21:53:17 +0000schuelermine(~Thunderbi@user/schuelermine) (Client Quit)
2026-06-30 21:53:02 +0000polykernel(~polykerne@user/polykernel) polykernel
2026-06-30 21:52:56 +0000schuelermine(~Thunderbi@user/schuelermine) schuelermine
2026-06-30 21:52:39 +0000schuelermine(~Thunderbi@user/schuelermine) (Client Quit)
2026-06-30 21:52:27 +0000Lord_of_Life(~Lord@user/lord-of-life/x-2819915) Lord_of_Life
2026-06-30 21:52:06 +0000tccq(~tccq@user/tccq) (Quit: connection reset by purr)
2026-06-30 21:52:05 +0000AlexNoo(~AlexNoo@178.34.151.183)
2026-06-30 21:51:59 +0000schuelermine(~Thunderbi@user/schuelermine) schuelermine
2026-06-30 21:50:31 +0000polykernel(~polykerne@user/polykernel) (Ping timeout: 276 seconds)
2026-06-30 21:49:43 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn
2026-06-30 21:45:27 +0000werneta(~werneta@71.83.160.242) werneta
2026-06-30 21:38:39 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 245 seconds)
2026-06-30 21:35:44 +0000takuan(~takuan@d8D86B9E9.access.telenet.be) (Ping timeout: 245 seconds)
2026-06-30 21:35:16 +0000sp1ff(~user@2601:1c2:4080:14c0:5df2:f2f4:8a07:70ec) sp1ff
2026-06-30 21:34:26 +0000marinelli(~weechat@gateway/tor-sasl/marinelli) marinelli
2026-06-30 21:34:21 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn
2026-06-30 21:33:31 +0000werneta(~werneta@71.83.160.242) (Ping timeout: 248 seconds)
2026-06-30 21:31:34 +0000schuelermine(~Thunderbi@user/schuelermine) (Ping timeout: 245 seconds)
2026-06-30 21:29:30 +0000takuan(~takuan@d8D86B9E9.access.telenet.be)
2026-06-30 21:29:17 +0000takuan(~takuan@d8D86B9E9.access.telenet.be) (Read error: Connection reset by peer)
2026-06-30 21:27:34 +0000schuelermine(~Thunderbi@user/schuelermine) schuelermine
2026-06-30 21:23:36 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 252 seconds)
2026-06-30 21:18:59 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn
2026-06-30 21:08:55 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) (Ping timeout: 276 seconds)
2026-06-30 21:05:16 +0000Katarushisu6(~Katarushi@finc-20-b2-v4wan-169598-cust1799.vm7.cable.virginm.net)
2026-06-30 21:03:38 +0000merijn(~merijn@host-cl.cgnat-g.v4.dfn.nl) merijn
2026-06-30 21:03:26 +0000 <int-e> ('p' for 'd' that is)
2026-06-30 21:02:44 +0000juri_(~juri@217-114-215-140.pool.ovpn.com) juri_
2026-06-30 21:02:41 +0000 <int-e> (unfortunately that's not a plausible typo. :) )
2026-06-30 21:02:12 +0000 <int-e> Well, it's not calle vibe coping for nothing
2026-06-30 21:01:31 +0000 <tomsmeding> yes
2026-06-30 21:01:15 +0000 <int-e> So... it feels better by an unspecified margin.
2026-06-30 21:01:09 +0000polykernel_polykernel
2026-06-30 21:01:09 +0000polykernel(~polykerne@user/polykernel) (Ping timeout: 245 seconds)
2026-06-30 21:00:13 +0000 <tomsmeding> subjectively improves output quality
2026-06-30 20:59:54 +0000 <int-e> I dislike the word "works" in this context, it's too unspecific
2026-06-30 20:59:37 +0000polykernel_(~polykerne@user/polykernel) polykernel
2026-06-30 20:59:06 +0000Katarushisu6(~Katarushi@finc-20-b2-v4wan-169598-cust1799.vm7.cable.virginm.net) (Quit: The Lounge - https://thelounge.chat)
2026-06-30 20:57:26 +0000 <tomsmeding> which, perhaps surprisingly, apparently works
2026-06-30 20:57:14 +0000 <tomsmeding> int-e: supposedly, the fancy ones also do some kind of socratic method stuff: have another instance of the LLM (with a different prompt) judge the output, feeding that back, etc
2026-06-30 20:56:51 +0000int-eshrugs
2026-06-30 20:56:29 +0000 <int-e> So the poor humans have to do less of that.
2026-06-30 20:56:14 +0000 <int-e> Anyway. The point was that as I understand it, the harness is a kind of lector. It'll catch the most obvious bullshit (code that fails to compile, test suites don't pass, linter outputs etc.) and reject stuff, and I suppose add it to the prompt (call it "refining the prompt" if you want to be fancy)