Creeta — AI developer tools & ecosystem news
For Analyst Deliverables, 3% Is Where the Best AI Tops Out
91 analyst tasks, 4 private scenarios. Claude Fable 5 leads at 1586 Elo but fully passes just 3% of criteria sets.
HiRO-ACE cuts climate emulation to 45 minutes — with a ceiling
Ai2's HiRO-ACE: ACE2S stochastic emulator + HiRO 32× diffusion downscaler. 3 km precipitation in 45 min. Apache-2.0.
Officially obsolete: the base_url trick for OpenRouter
0.2.4 adds parallel_tool_calls, pins openrouter SDK 0.9.2, and formalizes the OpenRouter adapter with correct provider attribution and telemetry.
Mistral OCR 4: the 72% is preference voting, not proof
OCR 4's 72% win rate: blind preference study, 600+ docs, undisclosed competitors, no published methodology.
AMIE Lands in Nature: The Talker-Thinker Split Worked
AMIE reaches disease management in Nature 2026. Two-LLM design, RxQA benchmark, and 100-scenario PCP comparison covered.
DeepSWE's top entry was gaming the grader
Datacurve's DeepSWE v1.1: scoreboard, grading loophole fix, and cost-efficiency breakdown across 9 AI coding agents.
SimpleMultiModalQueryEngine is deprecated. Here's the swap.
LlamaIndex 0.14.23 deprecates SimpleMultiModalQueryEngine, unifies rich-media RAG, and fixes workflow state bleed.
Apple called it Foundation Models. Reporters say Gemini.
Siri AI debuts at WWDC 2026 with a Foundation Models Swift API and a Gemini-linked cloud tier Apple has not confirmed.
Snowflake's CEO declared a tie. The iteration ledger didn't.
Snowflake CEO tested GLM-5.2 vs Claude Opus 4.7: 103 tasks, pass@3 near-tie, 2x token use, 5.7x cheaper output. Here's what the numbers actually mean for builders.
Compaction has no opt-out in 0.143.0. Here's what to adjust.
Codex 0.143.0-alpha.14 annotated: compaction opt-out removed, 61% fewer filesystem RPCs, new TOML source allowlists.
Three packages claim 'SkillsGuard'. One shipped malware.
The SkillsGuard that actually ships: AgentGuard v1.1.28. Four commands to first scan, 24 detection rules, known gaps.
Amazon Folded Apparel Printing Into Alexa. The AI Is Unnamed.
Amazon's Alexa now generates merch from a description. The image model powering it remains unattributed as of June 2026.
AI developer tools and ecosystem news for developers and technical founders