Hacker News: fabijanbajo

New comment by fabijanbajo in "Launch HN: Mireye (YC S26) – Infrastructure for Physical World AI Agents"

fabijanbajo — Fri, 04 Sep 2026 14:48:05 +0000

per-field freshness is the failure mode here, not coverage. blend sources and one record ends up with hours scraped last night sitting next to a phone number nobody has rechecked in two years

New comment by fabijanbajo in "Show HN: I built a search engine for 800 niche job boards"

fabijanbajo — Wed, 26 Aug 2026 06:36:47 +0000

do you dedup across boards, or is a board's page meant to show its own copy?

New comment by fabijanbajo in "Launch HN: Discovered Materials (YC P26) – AI agents to discover new materials"

fabijanbajo — Thu, 13 Aug 2026 15:38:37 +0000

package thermals end up setting the facility water bill.. what heat rejection costs in power and water mostly comes down to how cold the loop has to be: cold needs chillers and evaporative assist, warm can run on dry coolers. so resistance removed between die and coolant is headroom to run the loop warmer. curious if that's where your materials sit, and whether customers take the win as warmer supply temps or just more TDP..

Show HN: I graded 83 AI vendors on data residency, training and subprocessors

fabijanbajo — Thu, 13 Aug 2026 12:12:17 +0000

Article URL: https://sovereignairegistry.com

Comments URL: https://news.ycombinator.com/item?id=49284787

Points: 2

# Comments: 0

New comment by fabijanbajo in "Launch HN: Prized (YC S26) – Let non-engineer staff build secure internal tools"

fabijanbajo — Fri, 31 Jul 2026 07:44:07 +0000

the credentials-out-of-the-sandbox part is the easy half. the quieter failure is a tool that holds no keys and still renders rows this particular employee was never meant to see.. sign-in proves who someone is, it doesn't scope what the query returns.

does the scoped token narrow to the requesting user, or is it one service identity per connector with the row filtering left to whatever the agent generated?

Show HN: Tool that turns a CSV into an agent-run, searchable paywalled directory

fabijanbajo — Tue, 21 Jul 2026 11:58:10 +0000

Article URL: https://medspas.shipmore.io

Comments URL: https://news.ycombinator.com/item?id=48991099

Points: 1

# Comments: 0

New comment by fabijanbajo in "REO Trucks I4 4WD Pickup Truck Starts at $21,500"

fabijanbajo — Sun, 19 Jul 2026 08:51:03 +0000

i think im getting good at recognizing claude code designed landers

New comment by fabijanbajo in "Setting up your spare Mac for Claude Code to control, a step-by-step guide"

fabijanbajo — Sun, 19 Jul 2026 08:49:23 +0000

harvesting

New comment by fabijanbajo in "Show HN: Searchable directory of 22k+ products from worker-owned co-ops"

fabijanbajo — Thu, 02 Jul 2026 10:40:53 +0000

+1 to the combined all-products view with category tags..would make browsing way easier. Nice work

New comment by fabijanbajo in "Qwen 3.6 27B is the sweet spot for local development"

fabijanbajo — Tue, 30 Jun 2026 05:27:50 +0000

We need machines designed around wide memory + sustained inference thermals, not gaming/creator chassis we're borrowing. Until then "local dev" means clamshell + external fans.

New comment by fabijanbajo in "What happened after 2k people tried to hack my AI assistant"

fabijanbajo — Fri, 26 Jun 2026 05:07:11 +0000

how much of the win was the model versus the constraints?

New comment by fabijanbajo in "GLM-5.2 is a step change for open agents"

fabijanbajo — Thu, 25 Jun 2026 10:40:39 +0000

Agreed. Even just distilled versions of their frontier models would be a huge win for the open ecosystem

New comment by fabijanbajo in "Systems optimization should be part of CI/CD"

fabijanbajo — Wed, 24 Jun 2026 16:44:19 +0000

3–7× cheaper is the real win. 'Better on every problem' oversells it?

New comment by fabijanbajo in "Surprising economics of load-balanced systems"

fabijanbajo — Sat, 20 Jun 2026 08:02:22 +0000

The footnote on exponential vs. log-normal service times is the part I'd push on.. in production I almost never see exponential, and heavy tails change the picture. Curious if you've looked at how robust this is under realistic distributions