Top all-time · #7920
Senko Rašić
Personal blog · senko.net · on HN as senkoprogrammingwebai
Senko Rašić is a personal blog at senko.net about programming, web and ai. Since 2009, 9 different Hacker News readers have linked it 46 times, most often “Maybe in Python”. It is still writing: the last post was on 2026-11-01, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Senko Rašić's posts on the Jingle-based video chat in Google Talk and Gmail, and on a vibe-coded benchmark. The comments only link to the posts and do not judge the writing.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Maybe in Python3 people · 3 mentions · first linked 2014-05-01
- /vibecode-bench/2 people · 7 mentions · first linked 2026-06-03
What Hacker News says?
Opus 5.5 is neck-and-neck with Fable 5.1 and Astra 6 in my vibe-coding tests - maybe even better than Fable 5.1 Minecraft clone: https://senko.net/vibecode-bench/2026/voxel-opus-5.5.html (Opus 5.5) vs https://senko.net/vibecode-bench/2026/voxel-fable-5.1.html (Fable 5.1) vs https://senko.net/vibecode-bench/2026/voxel-gpt-6-astra.html (Astra 6) Warcraft clone: https://senko.net/vibecode-bench/2026/rts-opus-5.5.html (…
Comment linking /vibecode-bench/
on “Claude Opus 5.5”Submitted Django Setup using Nginx and Gunicorn as a story · 104 points
HN discussionHere it is: https://senko.net/vibecode-bench/2026/rts-gpt-5.6-sol.html Clearly much better than the Terra version. I'd say its on par with Fable, and the observed differencies are more due to random luck and open-ended prompt, rather than model capability. (Edit: after some more testing, perhaps not on par - somewhere between Opus and Fable, is a better description). Fable did better pathfinding and has more terrain…
Comment linking /vibecode-bench/2026/rts-gpt-5.6-sol.html
on “GPT-5.6”Submitted Type checking in Python as a story · 97 points
HN discussionI'd say Fable 5: https://senko.net/vibecode-bench/2026/rts-fable-5.html It even has enemies! (I'm not too mad about it not following my instructions because it can be fun to play :) And I generated that from Claude Code on my phone. Sonnet 5 also produced a pretty nice version. You can see all of them here: https://senko.net/vibecode-bench/
Comment linking /vibecode-bench/
on “GPT-5.6”Submitted MongoDB gotchas for the unaware user as a story · 83 points
HN discussionI love testing the new models by asking them to code a toy RTS game. Here's what Terra did: https://senko.net/vibecode-bench/2026/rts-gpt-5.6-terra.html (one try, in codex app, xhigh effort) Comparing this to other models, I find it similar to GPT-5.5 and a bit behind Sonnet 5. You can see how other models fared here: https://senko.net/vibecode-bench/ (you can also fetch the prompt and the the 5.6 Terra resulting co…
Comment linking /vibecode-bench/
on “GPT-5.6”Submitted Auto rsync local changes to remote server as a story · 45 points
HN discussionThe bug may be bash's, but it's the entire chain that makes it a serious one: http://senko.net/shellshock
Comment linking /shellshock
on “Not a bash bug”Submitted Using Git for web app deployment as a story · 38 points
HN discussionThe annoucement email itself: http://mail.jabber.org/pipermail/jingle/2011-June/001640.htm... This is great news. Google has been one of the driving forces behind Jingle, but as they were implementing it far in advance of being standardised, the drafts/standards have since changed. Other implementations have to maintain support for several close but not quite the same dialects. Google updating their software will ma…
Comment linking /en/gmail-videochat-the-good-the-bad-and-the-ugly/
on “Google switches GTalk's VOIP protocol to Jingle”Submitted Developer litmus test as a story · 18 points
HN discussionThere isn't, as I wasn't going for strictness, more like a playful challenge in the vein of Simon's SVG pelican. Between the two, Opus 4.8 seems more capable. But, I suspect the harness plays a large role here. It's possible the result would be as good if Codex ran 10+ agents and spent an hour on it. OpenAI and Anthropic usually fast-follow each other, so I wouldn't be surprised if Codex got the same capability in a…
Comment linking /vibecode-bench/2026/rts-codex-5.3.html
on “Claude Opus 4.8”Submitted If Linus started his kernel in 2010: Free Linux-like kernel sources for x86-64 as a story · 8 points
HN discussionI ran the Q4 quant (used with llama.cpp) though my "minesweeper" vibe-coding benchmark: https://senko.net/vibecode-bench/2026/minesweeper-gamma-4-12... The result is decent, but it had a few bizzare/trivial syntax errors I had to fix manually: it would do an extra closing bracket or paren a few times, and wanted to separate function definitions with comma. Not sure what that was about, but otherwise the output run j…
Comment linking /vibecode-bench/
on “Gemma 4 12B: A unified, encoder-free multimodal model”Submitted Learning Go as a story · 6 points
HN discussionI use Minecraft (and Warcraft and an arcade flying simulator) as a silly but directionally correct indication of the models' capabilitites. Compare Astra[0] with GPT 5.4[1] which was OpenAI's state of the art just six months ago. (all tests on more models with code and prompts available here: https://senko.net/vibecode-bench ) Yes, it's not a scientific benchmark but it's a good heuristic. For a better eval, create…
Comment linking /vibecode-bench/2026/rts-gpt-5.4.html
on “Recreating Minecraft Is Not a Benchmark”Submitted Twitter doesn't scale (for conversations) as a story · 3 points
HN discussionHaving tested K3, Qwen 3.8 max preview, Fable and Sol for the past few days, I partially agree. Don’t trust the benchmarks, and the Chinese models really are slow and token-inefficient. However they do seem very close to SOTA : I’d say roughly equal to previous gen (Opus 4.8, GPT 5.5). It’s yet another silly benchmark, but compare them here: https://senko.net/vibecode-bench/ I also had K3, Qwen3.8 and Fable (using K…
Comment linking /vibecode-bench/
on “Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA”Submitted Maybe in Python as a story · 2 points
HN discussionTheir implementation of all things Jingle came in advance of any specification, so it's not fair to call it NIH. See this comment for more info: http://senko.net/gmail-videochat-the-good-the-bad-and-the-ug...
Comment linking /gmail-videochat-the-good-the-bad-and-the-ugly/
on “Google Talk for Developers”Submitted Maybe in Python as a story · 2 points
HN discussionYes but not quite; they somewhat sidestepped Jingle standardisation process and extended then-current standard to suit their use case. They also primarily use(d) H.264/SVC which doesn't have readily usable free/open implementations. (more at my rant & google/xmpp dev comments here: http://senko.net/gmail-videochat-the-good-the-bad-and-the-ug... ) The good news is that since that announcement Google have been working…
Comment linking /gmail-videochat-the-good-the-bad-and-the-ugly/
on “Google Talk for Developers”Submitted Quickstart your Django projects in 60 seconds as a story · 2 points
HN discussionClickable links: http://en.co.de/ and http://senko.net/en/experiences-building-encode/
Comment linking /en/experiences-building-encode/
on “Ask HN: Please review my web app: online video converter”Submitted Django boilerplate project as a story · 2 points
HN discussionPaging senko, let's see Fable's oneshotted RTS! https://senko.net/vibecode-bench/
Comment linking /vibecode-bench/
on “Claude Fable 5”Submitted Fast WordPress/Nginx setup on a cheap VPS as a story · 2 points
HN discussionThe post mainly talks about coding from security point of view. Fair enough. In my own (limited) testing so far, Fable is the most capable model (for coding in general), and the most expensive. It pretty much saturated my "LLMCraft" benchmark to implement a mini RTS: https://senko.net/vibecode-bench/2026/rts-fable-5.html (prompt and results for other models here: https://senko.net/vibecode-bench/ ) That said, combin…
Comment linking /vibecode-bench/
on “Claude Fable 5: mid-tier results on coding tasks”Submitted Beyond Type Errors as a story · 1 points
HN discussion
