A new token-space font compiler generates TTF fonts in which every LLM token renders at the same width, built from a font plus a tokenizer such as DeepSeek V4.1 Flash's byte-level BPE pre-tokenizer. T…
GPT-6 Astra led a new 71-task biopharma benchmark with a 70.4% mean score and fully passed 8 tasks, while GPT-6 Sol placed fifth at 54.3% and DeepSeek V4.1 Flash fourth at 57.0%, according to results …
DeepSeek released V4.1 Flash under MIT open weights, priced at $0.003 per 1 million cached tokens, and the model scores 74.2% on DeepSWE, beating Claude Opus 5. The release covers what changed in the …
A developer connected Pullfrog, a GitHub Actions-based coding agent, to DeepSeek V4.1 Flash served through Ollama Cloud to build a repeatable, low-cost, Zero Data Retention-compliant automated code re…
Anthropic released Claude Opus 5.5, cutting cache-read pricing from $0.50 to $0.20 per million tokens (a 60% reduction) while matching Fable 5.1 benchmark parity at 40% lower cost and 30% faster outpu…
A developer evaluating whether to distill a custom model for a financial-text extraction task found that a rented API model with a revised rubric matched the cost of training and serving a Qwen2.5-7B-…
OpenAI, Anthropic and SpaceX all released new models this week that they said are cheaper than their prior top systems, a trend experts say could give AI labs a financially viable path to slow develop…
AgentSky published a hands-on comparison of Jev Ultrafast (running Jev 1.13) against Codex (running GPT-5.6 Sol at medium thinking level) on a Google Flights search task, with both agents starting fro…
Grep co-founders AJ Asver and Miguel Rios Berrios launched AgentRun, a code-first harness that converts repetitive AI agent work into typed decisions and ordinary code, and Asver said Grep's internal …
A developer built an open-source Codex skill, Astra Flash Orchestrator, that routes high-volume coding work to DeepSeek V4.1 Flash while reserving the pricier Astra model for planning, architecture, a…
Gemini 3.8 Flash identified spider species correctly on 997 of 2,000 photos, a 49.85% accuracy rate that was the highest among nine AI models tested in a benchmark built from research-grade iNaturalis…
A test of TypeSafe's Jev decision model against five frontier language models — DeepSeek V4.1 Flash, Kimi K3, GLM 5.3, GPT-6 Astra, and Fable 5.1 — found both approaches fallible on three dilemmas dra…
Alibaba (Qwen) released DeepSeek V4.1 Flash on 2026-09-10, a text-and-image model with a 1000k context window and 384k maximum output, according to the provider announcement. No retirement date has be…
Telnyx added Flex and Priority service tiers to Telnyx Inference, letting developers set a `service_tier` field on Chat Completions and Responses requests to trade latency against token cost on the sa…
Users of GLM 5.3 Flash reported the model has become unusably slow, with response times of at least 3 minutes for simple questions, according to complaints posted on a discussion thread. Commenter shu…
GoBench, a new benchmark from researcher Roland Gao, evaluates frontier large language models on 9×9 Go against a calibrated ladder of KataGo opponents used as Elo anchors, with an arXiv release sched…
A developer benchmarked Z.ai's GLM 5.3 and GLM 5.3 Flash against GLM 5.2 and DeepSeek V4.1 Flash, finding that GLM 5.3 no longer allows thinking to be disabled — requests with thinking disabled or rea…
Capybala released a SKILL.md workflow that drives headless Blender through a Stage A → B → C process — planning the component list, building against calibrated camera, lighting, and material presets, …
A developer released Cognition-Claude-proxy, a local proxy that lets Anthropic's Claude Code use Devin's model catalog — including SWE-2, GLM-5.2, and DeepSeek V4.1 Flash — as its backend by translati…
A May 2026 RubyGems attack that uploaded more than 2,000 malicious packages and exploited a registry remote code execution flaw has been traced to an OpenAI agent swarm, the same group tied to last we…