Žinutės

#8bit #riverraid #decisionmodels | Łukasz Skorwider | 20 comments

I don't know if there are still people here who remember the great #8bit computer game #RiverRaid. On the wave of the recent hype, I built a benchmark for #DecisionModels based on this game. I tested: Jev, Tev, GPT-6 Luna Decisions, Microsoft-Decider-1, Perplexity Decider v1.1 27B and Drex v1.5. Whether you want to see how decision models perform or reminisce about River Raid, I invite you to visit my YouTube channel. Link in a comment. | 20 comments on LinkedIn

LinkedInPerskaityta 2026-10-14 22:48

Vebinaras: atsiskaitymo langas, kuris parduoda

Spalio 15 d. nemokamas vebinaras e. parduotuvėms: kaip sutvarkyti atsiskaitymo langą, mažinti paliktų krepšelių skaičių ir didinti konversiją.

Perskaityta 2026-10-14 18:49

Caveman (YC F26) is now backed by Y Combinator It started as a joke: make Claude talk like a caveman so my AI bill stopped beating my grocery bill. 111,000 GitHub stars later, it's a company. And… | Julius Brussee | 216 comments

Caveman (YC F26) is now backed by Y Combinator It started as a joke: make Claude talk like a caveman so my AI bill stopped beating my grocery bill. 111,000 GitHub stars later, it's a company. And today we launched everything at once. Caveman 4.0 is out. → Say less. The original caveman voice. 63 tokens become 20. → Read less. Logs, JSON and test output shrink before the model reads them. 33.2% fewer input tokens across whole Claude Code sessions. → Auto (new). A model in your agent's picker that chooses the model and the effort for each ask. 54% cheaper on SWE-Together and SWE-Interact, same score, taking 50% less time. → Blocks (new). Agents write the same throwaway script every session. We counted one script written 394 times in a week on one machine. Blocks keeps it in your repo and hands it back. One test run: 397 tokens → 76. → Warm cache (new). Step away and your provider forgets your session, so the next message pays full price. Caveman keeps it warm while you pause. All of it i

LinkedInPerskaityta 2026-10-14 10:49

Redesigning source control at Anthropic

As our merges per day grew more than tenfold, source control became our biggest development bottleneck. Here, we share how we migrated to an in-house version control system in five months.

Perskaityta 2026-10-14 10:49