virushuo
@virushuo
Back to the 2006. Screeching voices of the minority.
Author «Illustrated History of Programming»
2.8K Following 63.4K Followers
20 years ago, my first startup was all about enterprise search. Two decades later, we’re still building search engines. The technology has shifted from NLP to NN and the users from humans to agents. but searching is still the core. opensource the fastest bm25 engine:
Show more
When you want to move from single agent SQLite on something like QMD, PostgreSQL is a great choice for multi agent and production quality, but not as snappy.
So we made it much more snappy with BM25 & open sourced it.
More soon for planetary scale sovereign agents
Show more
so we built psql_bm25s.
exact BM25 retrieval. native Postgres access method. ~23x faster than pg_search on the standard benchmark.
retrieval stops being a budget item. the harness stops rationing. the agent gets to look things up like it should have the whole time.
Show more
New research: long-running agents often fail by stopping too early, not because the model can't make progress.
We tested 5 harness designs across 8 long-horizon coding tasks.
Our new orchestration harness, Zenith, wins 5/8 at 43% the cost of the strongest baseline.
Show more
weekend project: 2x3090/vllm cyankiwi/Qwen3.6-27B-AWQ-BF16-INT4 200k context. swival as my coding agent.
As long as models keep getting more powerful via RL, distillation, and quantization, GPU depreciation will be much slower than expected. Even a 3090 will remain very useful
Show more
We are happy to share early results from Logos, our novel first-principles augmented intelligence system, that has enabled insightful results across domains.
We start with series of results in physics
Today's is a lovely result hiding in Special Relativity for 121 years.
Show more
Here's Qwen 3.6-35B-A3B v.s. Claude Opus 4.7 for "Generate an SVG of a flamingo riding a unicycle", in case you thought Qwen might be cheating at the pelican benchmark
