Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-11 · source-backed
Luu re-ran the widely-shared Alderson result (J at 70 tokens average vs Clojure's 109) and showed it was an artifact of trivial Rosetta Code problems. His replacements: implementing a full Zstd decoder from RFC specs with no tests, and the Pandoc task from ProgramBench scored against holdout tests, across ~24 languages using GPT-5.6 Sol at medium and ultra effort. Pre-registered predictions held. The dynamic-language advantage and the "weird language" advantage both vanish at real complexity, and a weak-to-moderate positive correlation emerges between language popularity and solution quality. Pick for ecosystem depth, not token thrift.
Each link below shares sources, entities, or timing with this story.
GPT-5.6 Sol Ultra tops out at 91.9%. The public leaderboard is led by Codex CLI plus GPT-5.5 at 83.4%, with Claude Code plus Opus 4.8 the top usable Claude pairing at 78.9%, and Gemini CLI plus Gemini 3.1 Pro at 70.7% (Morph). There are now roughly 35 actively maintained CLI c...
Terminal-Bench 2.1 results (entries dated June 17) put Codex CLI on GPT-5.5 first at 83.4%, Claude Code on Fable 5 second at 83.1%, and Claude Code on Opus 4.8 at 78.9%. The asterisk matters more than the ranking: Fable 5 and Mythos 5 have been export-suspended since June 12,...
DeepClaude hit 470 points on Hacker News. It swaps Claude Code's API backend to DeepSeek V4 Pro while preserving the full agent loop: file editing, bash execution, git tooling, the whole workflow. DeepSeek V4 Pro scores 96.4% on LiveCodeBench at a fraction of Anthropic's prici...
$3,054 against $38,370. Same benchmark, better score. Praxist (arXiv 2608.25955, submitted August 26) replaces per-attempt agent memory with a typed evidence graph of findings, plus lane-structured frontiers and agendas, so later attempts inherit validated mechanisms rather th...
At Black Hat USA 2026, NVIDIA researchers demonstrated a 56% exploit success rate against AI agents, matching GPT-4o, Claude, and Gemini, at 70 to 125 times lower cost with full local privacy (Straiker). The economics of automated agent exploitation had been implicitly protect...
diegosouzapw/OmniRoute added 1,343 stars on July 20, a single MIT-licensed gateway across 268+ providers (50+ free) and 500+ models including Claude, GPT, Gemini, Kimi K3, GLM and DeepSeek, wired for Claude Code, Codex, Cursor, Cline and Copilot. Quota-aware automatic fallback...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.