cd/sources/runtimewire-auto-discovered· home› sources› Runtimewire (auto-discovered)
cat /sources/runtimewire-auto-discovered.feed | wc -l → 1889

Runtimewire (auto-discovered)

articles 1889 domain runtimewire.com → page 71/95 feed RSS
14:06
2026-07-16
runtimewire.com
artificial-intelligence

Head to head: Kimi-K2.7-Code vs gpt-5.4

In a head-to-head benchmark of 12 fresh text tasks, Kimi-K2.7-Code scored 103.5 against gpt-5.4's 101.5, with only 50% confidence that either model is better, resulting in a tie. Kimi edged ahead on c…

07:17
2026-07-16
runtimewire.com
artificial-intelligence

Prolo raises £4.2M to build AI procurement for construction SMEs

Prolo, a London-based AI procurement platform for small and medium-sized construction firms, has raised £4.2 million in seed funding led by Triple Point Ventures with participation from a16z Scout Fun…

03:16
2026-07-16
runtimewire.com
artificial-intelligence

RuntimeWire – Startup intelligence for the AI economy

MIT researchers have published a non-generative test for CSAM-tuned AI models called Gaussian probing, which checks LoRA-adapted diffusion models by reading internal activations instead of producing i…

21:14
2026-07-15
runtimewire.com
artificial-intelligence

Whatnot acquires Shaped to speed up live-shopping recommendations

Whatnot acquired Shaped, a machine-learning company for real-time recommendations and search, to accelerate live-shopping discovery. Shaped founder Tullie Murrell and nearly a dozen engineers and AI r…

19:33
2026-07-15
runtimewire.com
artificial-intelligence

DeepSeek's V4-Pro price cut exposes the agent margin problem

DeepSeek's 75% price cut on its V4-Pro model, reported in May 2026, exposes a deeper problem for AI founders: agentic products consume tokens far faster than model prices drop, according to a VentureB…

14:15
2026-07-15
runtimewire.com
large-language-models

Head to head: Kimi-K2.7-Code vs gpt-5.4-mini

Kimi-K2.7-Code defeated gpt-5.4-mini 100.0 to 98.8 in a head-to-head test of 12 fresh text tasks, with an 83% confidence verdict and a 6-3-3 win-loss-tie record. The evaluation, scored by gpt-5.4, fou…

10:06
2026-07-15
runtimewire.com
ai-startups

Refer raises $7.5 million for candidate-paid AI recruiting

Refer, an AI recruiting startup founded by Andre Hamra, has raised a previously unannounced $7.5 million seed round, bringing total disclosed funding to about $10 million. The San Francisco-based comp…

← prev page 71 / 95 next →