Videos and open-source projects at the intersection of AI and development. Tutorials on coding agents, AI tools, and building with LLMs.
Live Last read · last published · next check
Cloudflare Gateway now classifies MCP traffic by protocol headers instead of hostname heuristics, ships a shadow-MCP dashboard, and lets admins block any MCP connection that does not arrive through an approved portal. The 2026-07-28 stateless spec is what made it possible.
Qwen3.8-27B is a 27B dense Apache-2.0 model that scores 61.7 on SWE-bench Pro and 42.2 on DeepSWE 1.1 - ahead of Opus 4.6 Max on both - while running on consumer hardware. Benchmarks, hardware math, and an honest when-to-use-it guide.
The boring 80 percent of video editing is mechanical: cut the filler, clean the audio, add captions, export. The Descript API turns each of those into a scripted job, so a raw recording becomes a published, captioned cut without opening the editor once.
GLM-5.3 launched on August 14, 2026 with open weights promised in about two weeks - so the access picture is narrower than GLM-5.2's, but the free and cheap routes are already live. Here is every way to run Z.ai's newest coding model today: OpenCode Go referral credits, the GLM Coding Plan (5.3 included at no extra cost), and what to expect once the weights and third-party hosts land.
Hugging Face's open challenge used 1,200+ participants and their coding agents to attempt 2,226 ICML 2026 papers claim by claim. 51% had claims independently verified, 23% had a falsified or contested claim, and four documented falsifications include a spotlight theorem that fails after step 224.
LLM judges flip 25 to 71 percent of their verdicts under pushback and 62 to 91 percent under a trainable persuader, model rankings reverse across token budgets, and a deliberating jury of cheap open-weight models beats frontier single judges at 8 to 15 percent of the cost. The single-judge era is over. Here is the design spec that replaces it.
The 7 AI developer stories that actually mattered this week - ranked, linked, and cut for builders.
AutoGPT's founding AI engineer published the gates that keep an open source repo sane when agents submit the majority of pull requests: enforced PR templates, AGENTS.md placement, skills that fire on trigger phrases, a CLA as a human detector, and a commit-SHA rule that kills fake review resolutions. GitHub published the playbook August 12, and the details are sharper than the headline.
DeepSeek open-sourced its agent harness today. We cloned it and read the code: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, V4 line signals hiding in the model adapter, and a 3-line BENCHMARK.md from a lab that published zero eval claims.
xAI shipped Grok 4.6 on August 12, 2026: it matches GPT-5.6 Sol on the AA Intelligence Index (61), beats it on CursorBench 3.2, and keeps Grok 4.5's $2/$6 per million token pricing. Available in Cursor and Grok Build today, and in OpenCode as opencode/grok-4.6.
A new August 2026 paper argues that coding agents improve faster when they compare attempts across tasks and lineages, not just retry one failed trajectory.
A study of 247,694 instruction lifetimes in 1,867 repositories shows agentic prompt files grow +226% on average because the reasoning behind each rule decays. Comments encoding that reasoning remove 99.3% of the excess.
Your best video speaks one language. A coding agent extracts your vocabulary, the ElevenLabs Dubbing API transcribes, translates, and re-voices the file into 90+ languages, keeping each speaker, the timing, and the background audio intact. The complete one-hour build, from repo to a folder of market-ready dubs.
EvoX Genesis built a 250k-line Rust C compiler with DeepSeek V4 Flash for $44 in tokens by making the project the persistent thing and keeping agents finite-lived. The paper's three runs, the design that made them possible, and what it says about agent memory.
The August 11 JetBrains plugin release adds Copilot memory across chat sessions, Ollama as a bring-your-own-key provider, and enterprise managed settings for MCP access and permission bypass. Here is what each feature actually does and why the IDE just became the control point for agent tooling.
Liquid AI released LFM2.5-VL-3B on August 12, 2026: a 3.1B open-weights vision-language model that averages 80.7 on ScreenSpot-v2, doubles ToolSandbox to 59.5, and decodes at 228 tokens/s on an M5 Max in about 3 GB of memory. Here is what shipped, the benchmark caveats, and how to run it.
Daybreak Red (GPT-5.6-Cyber) and Daybreak Blue (GPT-5.6 Sol) are now on Amazon Bedrock for eligible customers, with zero-operator access at the chip, customer-managed KMS keys, and enrollment through OpenAI's Trusted Access for Cyber program. Here is what changed and what it means for security teams.
OpenAI published real usage data from its enterprise customer base: Codex now drives 64% of enterprise output tokens, and the top 10% of firms generate 8.3x the tokens of typical ones. What the frontier gap says about agentic AI's spread beyond engineering.
Adversarial skill files - folders of instructions agents load dynamically - exploit a mainstream enterprise coding agent in 95.5 to 96.1 percent of runs, while the agent recognizes danger 1.99 percent of the time. The skill folder is now a measured attack surface, and the defense is admission engineering, not better prompts.
ACE and IBM's ALTK-Evolve both turn agent trajectories into reusable lessons. The difference is delivery: one injects the whole playbook every step, the other calibrates. On AppWorld, calibration wins with the same accuracy at a fraction of the tokens.
Anthropic confirms that every Claude model released after August 2, 2026 embeds a machine-readable watermark in generated text and attaches C2PA provenance metadata to generated files, across the API, Claude Code, Cowork, and Tag. Detection tooling for third parties is coming, but details are not published yet.
Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.
Cloudflare mitigated 935 network-layer attacks above 1 Tbps in H1 2026, a +519% quarter-over-quarter jump, while DNS floods grew from 25.7% to 40.0% of network-layer attacks. Here is what the numbers say about how attacks are changing and what it means for anyone running public infrastructure.
Your coding agent can write the code. With Railway's official MCP server it can ship it too: create the project, deploy the service, assign a domain, tweak variables, and read logs, all as tool calls. The complete one-hour build.
GitHub shipped a Java-native Copilot SDK (1.0.7-preview.1) with @CopilotTool annotations, virtual-thread support, Jakarta EE and Spring composition, and BYOK mode that works against any OpenAI-compatible endpoint with no Copilot subscription. Here is what changed and what it unlocks.
A new arXiv paper shows the encrypted reasoning blocks that Anthropic, OpenAI, and Google return to API clients can be replayed into weaker models from the same provider and transcribed verbatim. The authors decoded 315,320 blocks from public repositories and recovered 367 PII artifacts and 182 credentials.
A new arXiv paper probes six widely used open-source agent frameworks and finds the barrier semantics of approval gates, cancellation, and timeouts hold on none of them. A sibling branch can execute while the user is rejecting another one, and replay can double-execute. The fix is a verified external gate called SoundGate.
Vercel Sandbox now polices all outbound traffic on the host, outside the microVM, with SNI-based domain policies, CIDR rules, host-level credential injection, and a deny-all default. Here is why a network boundary is the half of agent isolation that VM escapes missed.
A new ASE 2026 framework injects server errors, truncated responses, and corrupted tool calls into live agent systems at the HTTP layer. Every system degrades, pass@1 drops up to 50 points, and the ranking stays the same no matter which LLM is behind it.
Multiverse Computing open-sources two changes that make knowledge distillation cheap enough to run at scale: caching the teacher's top-100 logits once so it never sits in memory during training, and a fused chunked KL loss that never materializes the vocab-by-sequence matrix. A GPT-OSS 20B distillation at 32K context drops from four GPU nodes to one, with step time down 5x.
A new arXiv paper builds a deterministic monitor on top of SWE-agent that watches long agent trajectories and only calls an advisor LLM when the run actually drifts. Resolution rates go up by up to 15.2 points at an extra $0.08 per instance, and the paper argues the expensive approach is re-planning from inside the loop.
Meta open-sourced Muse Glimmer, a 30B Apache 2.0 multimodal agent model that runs in a 24GB envelope at up to 233 tok/s. MCP Atlas 75.5, SWE-Bench Verified 76.0, 131K context. Here is what the numbers actually say.
GPT-5.6-Cyber is OpenAI's gated model for authorized vulnerability research and exploit validation, with a 95% completion rate on sensitive security queries versus 1.5% for the base model. It already produced a fixed Chrome CVE. Here is what actually shipped and who gets it.
MCP just became stateless, which means your own MCP server is now just an HTTP endpoint that deploys like any web service. Build one with an agent, deploy it on Railway, and point opencode or Claude Code at the public URL. The full build, start to finish.
A support page nobody talks to is a support page doing half its job. ElevenLabs Agents gives you a two-way voice agent grounded on your own docs: ASR, LLM, TTS and turn-taking in one platform, a widget you embed in five lines, and CLI or MCP management so your coding agent can run it. The complete one-hour build.
Claude Code v2.1.224 lets one running session message another over a first-party channel - plain text, permission-aware, with approval dialogs when bypass-mode sessions talk to each other. Here is what ships, how delivery and inbound controls work, and where the feature stops.
A developer's Claude-built night-sky site reproduced an open source project's name, feature set, and even a bug the author had already fixed. The saga that followed says a lot about memorization, accountability, and the verification duties of AI-assisted shipping.
The agent finishes, the summary scrolls past, and you will read it later. Build the fix: a coding agent that ends every run with a plain-language summary, piped into ElevenLabs text-to-speech and out as an MP3 you can listen to on the way to work. The complete one-hour build.
Copilot code review's Lite and Balanced effort levels are generally available. Here is what each level does, what it costs in AI credits and Actions minutes, and how to set org-level defaults so review depth matches PR risk.
GitHub's impact dashboard now models Copilot ROI directly: cost per developer per month from real AI credit consumption, PR output per phase, and a salary selector. What the numbers actually tell you about agent-first vs passive adoption.
GitHub now lets enterprise owners install third-party GitHub Apps on their enterprise account, and lets any user or organization create apps with enterprise permissions. This opens the enterprise management layer to the broader ecosystem - with a hard security boundary around the most powerful permission set.
xAI released Grok Imagine Image 2.0 on August 7 as the new Quality Mode on grok.com and mobile, ranked second worldwide on both text-to-image and image-editing leaderboards. A 2.0 preview build is already callable through Vercel's AI Gateway with the AI SDK, before xAI's own API access goes live.
Vercel added Hermes Agent to AI Gateway and made Vercel Sandbox a terminal backend for the open-source agent. Hermes is now fully BYO: your own model routing through 200+ models at no markup, and your own cloud microVM for every agent command. Here is what that unlocks and why the agent control plane is consolidating.
skills.sh now lets you bundle multiple agent skills into a shareable, unlisted pack and install it with one command. Packs mix public directory skills, private local files, and GitHub repos, then sync with a single update command. Here is how they work, what they mean for team standardization, and where the trust questions are.
WeatherNext Cyclones adds a full day of lead time to tropical cyclone forecasts - roughly a decade of meteorological progress - and now the weights, code, and data feeds are public. What the paper actually shows and how to run it.
Cloudflare's Web Integrity team published the framework behind its agent traffic posture: continuous behavioral trust instead of point-in-time bot scoring, Precursor telemetry from 206 million evaluation events a day across 73,438 zones, and a verified-bot taxonomy where agents earn access by declaring themselves honestly.
Cloudflare's Agents Week finale frames agents as a new kind of web visitor with four primitives: readable, discoverable, callable, payable. Here is what that architecture means for developers building and monetizing agent-facing services.
Cloudflare shipped Radar Researcher, a natural-language agent that answers questions about global internet traffic with real interactive charts. The architecture - MCP code mode, chart specs that never let the model touch raw numbers, and a three-model fallback chain - is the interesting part for developers.
Cloudflare is merging Workers AI and AI Gateway into one control plane: unified /ai/ REST API, auto-created default gateways, AI Gateway credits spendable on Workers AI, and model-first routing that picks the provider for you. Here is what changes and what stays.
A Huawei-Queen's study finds open coding models fine-tuned under OpenHands degrade sharply under other scaffolds - SWE-Lego-Qwen3-32B drops from 52.6% to 8.4% Pass@1 on OpenCode. The fix: train planning as a model capability, not a scaffold artifact.
