Hacker News: jascha_eng

New comment by jascha_eng in "Is Opus 5.5 nerfed? Thinking patterns changed on November 3"

jascha_eng — Mon, 09 Nov 2026 18:18:12 +0000

Sadly this thing stopped running a few weeks ago, the propduct half life is truly low these days otherwise wed have some data to rely on: https://marginlab.ai/trackers/claude-code/

New comment by jascha_eng in "Gemini 4 Carbon"

jascha_eng — Wed, 28 Oct 2026 17:28:49 +0000

What makes me most excited is that we probably get fable 5.5 soon with the IPO. Which is going to surpass this again. But cool to see progress!

New comment by jascha_eng in "Software may be getting worse, but it used to be horrible"

jascha_eng — Tue, 27 Oct 2026 12:49:13 +0000

huh? autosave, bsod, security the client side hacks of gaming how is any of this a hardware improvement. Software got a lot better.

Of course hardware also got better but software also got a let better at working around the hardwares quirks.

New comment by jascha_eng in "Kimi K3.1 scores 55 on Artificial Analysis, placed on the Pareto line"

jascha_eng — Fri, 23 Oct 2026 20:46:23 +0000

+1 for the omniscience benchmark!

Although even this one needs to be taken with a grain of salt. Fable/Opus still act very differently to Astra and Argon imo. But maybe it's just because I am used to these. I wouldn't clearly put them above each other though, although I still prefer anthropics models, but that could be simply out of comfort.

New comment by jascha_eng in "PingCap TiDB Leaks"

jascha_eng — Thu, 22 Oct 2026 10:37:22 +0000

yeh running some automatic scripts against public urls to check if https is enabled and scanning if there are public s3 buckets is barely any better than a security linter.

There are some teams that are better than this, but they are rare.

New comment by jascha_eng in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

jascha_eng — Wed, 14 Oct 2026 13:26:11 +0000

https://news.ycombinator.com/item?id=50086249

New comment by jascha_eng in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

jascha_eng — Wed, 14 Oct 2026 13:12:32 +0000

Btw, I do work for Tiger Data/timescale, but am not at all associated with this team. I just found this release really exciting.

I sent the thread to Erik (the main contributor) though, so if you have feedback or questions, good chance that he'll see it.

New comment by jascha_eng in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

jascha_eng — Wed, 14 Oct 2026 13:10:27 +0000

Well you can always move to tiger cloud if you want it managed :) And this is PostgreSQL licensed just like our pg_textsearch which has been adopted to Googles AlloyDB and microsofts HorizonDB already, so there is hope!

New comment by jascha_eng in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

jascha_eng — Wed, 14 Oct 2026 13:06:01 +0000

benchmarks are in the blog post and the benchmarking suite is also open sourced alongside it.

New comment by jascha_eng in "Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW"

jascha_eng — Wed, 14 Oct 2026 11:55:25 +0000

from the accompanying blog post: https://www.tigerdata.com/blog/announcing-pg_vectorsearch-sc...

> TLDR: We are launching pg_vectorsearch, a new open-source PostgreSQL extension that makes vector search dramatically faster and more cost-efficient. Its new PRISM index uses partitioning and compression instead of HNSW's graph-based approach, delivering faster queries with a fraction of the memory and significantly faster index builds. At 100 million vectors, PRISM achieved 6 ms query latency on a machine with 4× less memory than HNSW, with index builds over 20× faster.

Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW

jascha_eng — Wed, 14 Oct 2026 11:47:53 +0000

Article URL: https://github.com/timescale/pg_vectorsearch

Comments URL: https://news.ycombinator.com/item?id=50086165

Points: 213

# Comments: 53

Pg_vectorsearch: Scalable Open-Source Vector Search in PostgreSQL

jascha_eng — Tue, 13 Oct 2026 20:03:03 +0000

Article URL: https://www.tigerdata.com/blog/announcing-pg_vectorsearch-scalable-open-source-vector-search-postgresql

Comments URL: https://news.ycombinator.com/item?id=50077818

Points: 2

# Comments: 0

New comment by jascha_eng in "Mistral Large 4"

jascha_eng — Tue, 06 Oct 2026 15:30:57 +0000

Imo omniscience correlates better to how useful the model is in practice than the intelligence index. But you have to use both together of course.

New comment by jascha_eng in "Mistral Large 4"

jascha_eng — Tue, 06 Oct 2026 14:19:19 +0000

-5 on omniscience? https://artificialanalysis.ai/evaluations/omniscience

That's not particularly great.

That said I love that they don't seem to restrict cyber capabilities to any degree and even lean into it.

If the best model for cyber attacks is open for everyone to use it just makes us all safer I think. Of course you then also HAVE to use it or otherwise you're vulnerable, which is a great distribution play.

New comment by jascha_eng in "Livenerf: Has Opus 5.5 been nerfed yet?"

jascha_eng — Tue, 29 Sep 2026 23:37:19 +0000

Yeh it's absurd that people claim this all the time. It's some crazy conspiracy theory and when you ask for examples nothing ever shows up.

It would be economical suicide from anthropic and OpenAI to actually need models intentionally.

But hey I guess it's hard with technology that truly seems like magic. People say if you'd bring electricity to the middle ages you'd be called a witch and burned. The same is happening to the model labs here because they are bringing tech that the world isn't ready for yet.

New comment by jascha_eng in "Drawgent: Coding agent on a live Excalidraw canvas"

jascha_eng — Sat, 26 Sep 2026 20:48:40 +0000

I played around a bit with pencil.devs mcp integration before: https://www.pen.dev/

Which was at least fun for a bit although I failed to really see the use after models became better at designing themselves.

New comment by jascha_eng in "Drawgent: Coding agent on a live Excalidraw canvas"

jascha_eng — Sat, 26 Sep 2026 18:44:49 +0000

MCP is the answer but it's only really worth it if you product is reasonably complex e.g. n8n has a community MCP fully for this reason.

New comment by jascha_eng in "Grok 4.7"

jascha_eng — Mon, 21 Sep 2026 19:21:42 +0000

32 on the omniscience index. Not terrible but far from Astra and fable: https://artificialanalysis.ai/evaluations/omniscience

New comment by jascha_eng in "I am often wrong"

jascha_eng — Sun, 20 Sep 2026 19:00:02 +0000

That's what it took to finally support Agents.md I guess. Boris had to blog about having made a mistake.

How about you stop taking things so personal instead and let others steer more.

New comment by jascha_eng in "Ask HN: What are you working on? (September 2026)"

jascha_eng — Mon, 14 Sep 2026 02:10:06 +0000

Self hosted database access management, think Code Reviews for SQL Statements for when your devs need to go to prod: https://github.com/kviklet/kviklet

Recently cleaned up my postgres proxy and built a MySQL wire proxy so that you can use psql/datagrip as a dev but every statement is still logged. With SSO and no password sharing ofc!