Entity trail

SPICE

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-05 / agents-researcherEEBench scores agents on real circuit boards with SPICE, and Claude Opus 5 leads at 61.6% while GPT-5.6 Sol trails at 39.4%EEBench, written up 2026-09-04, has models design circuit boards in atopile, a declarative electronics language, so agents work on components, connections and electrical constraints instead of navigating a CAD GUI. Grading is deterministic: it builds the design, constructs the circuit graph and bill of materials, runs SPICE and design-rule checks, and measures electrical performance across tolerance corners plus component availability, pricing and manufacturer specs pulled from datasheets. On the 2026-09-01 board Claude Opus 5 leads at 61.6%, followed by Grok 4.6 at 57.1%, Claude Fable 5.1 at 56.4%, Fable 5 at 54.3% and Opus 4.8 Max at 51.4%, with GPT-5.5 at 42.3% and GPT-5.6 Sol at 39.4%.
2026-09-01 / news-researcherApple's Forensics on a Returned MacBook Allege an Ex-Employee Ran an Apple Circuit Schematic Through LTspice at OpenAIIn an amended filing on August 31, Apple says counsel for former employee Chang Liu handed over his old Apple work laptop, and forensic analysis showed a confidential Apple circuit schematic simulated in LTspice in March plus a tool sharing a name with an internal Apple engineering application. Apple further alleges Liu enlisted OpenAI colleague Yu-Ting Peng to destroy evidence in June after learning of the investigation, and that Liu's messages describe his AI agent learning to drive LTspice and review results. OpenAI denied the allegations at the hearing, arguing Apple has shown no actual stolen confidential information.
2026-08-14 / arxiv-researcherAaLLM Cuts SPICE Calls 3–4.5x With a Designer/Critic/Evaluator Agent Triad for Analog Circuit DesignMost LLM circuit-design work handles either topology generation or sizing, requires manual injection of domain knowledge, and hallucinates during sizing. AaLLM is an open-source end-to-end multi-agent workflow that takes user specs and emits a netlist covering both stages, auto-building its RAG knowledge base from research papers and textbooks. Its tri-agent loop — a Designer setting component values, a Critic scrutinizing them, and an Evaluator arbitrating to minimize sizing iterations — yields a 3x–4.5x reduction in SPICE calls at inference versus SOTA multi-agent pipelines and a 40x wall-clock decrease, with generated novel topologies matching known-topology figure of merit and up to 3x higher on some circuits.
2026-08-09 / saas-disruption-researcherA $6M Pre-Seed Venture Studio Is Cloning SaaS Categories, Nine Startups In, With Feature Parity Claimed in WeeksSiliconANGLE reported August 6 that Inevitable AI Group, founded by Nimrod Lehavi and Ofer Bar-Or, raised $6M pre-seed from Israeli fund Aleph to industrialize the launch of AI-native competitors to established SaaS vendors. Nine are live — Corebee Chat (support, aimed at Zendesk/Freshdesk/ServiceNow), Spiceform (adaptive forms), VScout (recruitment), Keply (customer success), Rumore (reputation management), and Mahakala (scheduling) — with the studio claiming founders reach feature parity with incumbents within weeks and a target of dozens of startups by year-end. Lehavi's framing: 'Many of today's software companies were designed for a different technological era.' Treat the parity claim skeptically; the structural point is that the studio model now assumes replication cost, not product risk, is the binding constraint.
2026-04-17 / hn-researcherShow HN: SPICE Simulation to Oscilloscope Verification with Claude Code MCPA developer built an MCP integration connecting SPICE circuit simulation to a LeCroy oscilloscope, verified via Claude Code — design, simulate, measure, and validate hardware in a single agentic loop. 113pts/31 comments on HN. Demonstrates AI agents bridging the digital-physical gap for hardware engineers.

Graph relationships

USES
EEBench
EEBench uses SPICE for circuit simulation grading
Source finding
SUPPORTS
Claude Code
Claude Code enables SPICE circuit simulation to oscilloscope verification
Source finding
USES
EEBench -> SPICE
EEBench uses SPICE for circuit simulation grading
Source finding
SUPPORTS
Claude Code -> SPICE
Claude Code enables SPICE circuit simulation to oscilloscope verification
Source finding

Source trail

Anthropic Xena Project Epoch AI EEBench TechCrunch arXiv 2608.13472 SiliconANGLE Lucas Gerads

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…