joithan

[joithan @jothantranston]

Shopify is shutting down Stocky on Aug 31, 2026. Products and POs migrate fine — supplier records don't export at all. Shopify's own docs say to re-enter them by hand.

[Theo - t3.gg @theo]

Xcode is legitimately one of the worst pieces of software ever made. Their entire platform is gimped by the worst developer tooling still distributed in the 2020's

I cannot fathom how Apple stays ahead with such a blatant lack of care for developer tools

[joithan @jothantranston]

@khongnt62 @thsottiaux i am using the cli on my macbook air no problems it normal at like 8gb of ram? for like 5-6 sessions coding etc?

[joithan @jothantranston]

FRRRRR

[Statusnone @Statusnone420]

I know you guys said otherwise, but please reconsider not reintroducing the 5h limits. Unless there is some behind the scenes technical reason for the limitation, let people burn their weekly at any time, in whatever cadence fits their life and schedule. Being a dev is hard enough, having to work around 5h windows is unhealthy for us and I've been getting better sleep and feel less anxious to "maximize my 5h window" since y'all got rid of it. A lot of other people agree. Please dont make us go back.

[Composio @composio]

We ran Kimi K3 through 3 agent harnesses (Claude Code, Hermes, Kimi Code) on 28 identical tasks.

All 3 harnesses completed the tasks at similar success rates, but the interesting story is token efficiency: the same task cost up to 30x more tokens depending on the harness. 🧵🧵

[Tibo @thsottiaux]

Hello people of Sol! I've reset usage limits for all ChatGPT Work and Codex users. Together with that, a quick update on GPT-5.6 Sol usage limits.

Over the past few weeks, many of you have told us that Sol was using your Codex limits faster than expected. To be clear, we have not reduced usage on any subscription plans.

We’ve been digging into what was happening and have landed several improvements. As a result, we expect your usage to last around 18% longer during typical use of Sol. Some of you should already see significantly larger improvements from today. Tomorrow, we’ll also restore the five-hour limit that we temporarily paused while investigating.

Here’s what we found:
- GPT-5.6 Sol is much more willing to work for longer, make additional tool calls, and coordinate complex workflows across tools and subagents. That makes it better at solving hard problems, but some tasks were using far more than we intended.
- Sol also works harder at the same reasoning effort than previous models. High on Sol can use more tokens than High did on GPT-5.5.
- Programmatic tool calling, also referred to as code mode, gives Sol much more flexibility to run tool calls in parallel or continue working while waiting. But it also led to more responses per turn, more cached input tokens, and higher usage than expected.
- This was particularly noticeable when Sol was waiting for tool calls to finish or running many web searches. We’ve improved how we handle both cases and are continuing to make code mode more efficient.
- The impact was also very uneven. The median user actually found Sol quite token efficient, while some power users working on harder tasks saw their usage drain much faster. We were very focused on average and median usage before launch and missed some cases where the long tail could use significantly more usage.

Sol is a significant step forward in what Codex can do, but capability and efficiency do not always improve at the same pace, and some issues only become clear once people are using the model at real-world scale. We should have recognized this sooner and been more upfront about it.

You keep pushing the frontier and we’ll keep improving efficiency and sharing updates as we go.

[ST @SerenaTaN5]

sell ur remaining claude subscription token

[joithan @jothantranston]

@aryanXmahajan half of this has open source or self hosted alternatives or can be done with claude?

[kuro @abue_ammar]

🚀 Introducing Tinycast! A tiny, blazing-fast, fully native written in swift Raycast alternative.

• < 100MB RAM & 3MB on disk
• Unlimited clipboard history
• Import everything from Raycast
• Free & open source
• No account, No telemetry. No bullshit
https://t.co/7SsXkdOY2y

[joithan @jothantranston]

OPUS 5 or GROK 4.5?

[joithan @jothantranston]

is not common knowledge been doing this for a while with opencode api key

[Alvaro Cintas @dr_cintas]

your AI agent can watch any video now - paste a URL and it sees every frame, hears every word, all for free 🤯

bradautomates/claude-video gives Claude the ability to watch YouTube, Loom, TikTok, local files - anything yt-dlp supports

what people actually use it for:

→ analyze a competitor launch - what hook, what visuals, what structure
→ debug from a screen recording - Claude reads the exact frame where it breaks
→ summarize a 49-min talk in 30 seconds with frame-accurate timestamps
→ strip the hype from product videos - "what's actually new, skip the pitch"

the mechanism: yt-dlp pulls free captions first (zero cost). ffmpeg extracts frames at scene-aware intervals - not uniform sampling, so you don't waste tokens on 12 identical frames of the same slide. Claude reads every frame as an image with timestamp markers. Groq Whisper only kicks in when a video has no caption track

how to set up (3 min):

> claude code: /plugin marketplace add bradautomates/claude-video then /plugin install watch@claude-video
> or npx skills add bradautomates/claude-video -g for codex, cursor, gemini cli
> dependencies auto-install on macOS via brew

two caveats: free captions cover most but not all videos. past 10 min use --start/--end for focused sections or the token-burner mode for full coverage

your buddy still watches every tutorial at 2x speed taking manual notes. you paste a URL and your agent extracts the substance in seconds for $0

[Elon Musk @elonmusk]

Next month, every line of code touching the 𝕏 system will be open source and third-party audited.

Only total transparency deserves trust.

[Elon Musk @elonmusk]

Grok 4.6 in 2 weeks and Grok 4.7 in 4 weeks

[joithan @jothantranston]

DOCUMENT EXTRACTION CHANGED FOREVER

LangExtract turns unstructured documents into structured information with source-grounded LLM extraction and reviewable output.

> Maps every extraction to its exact source-text location for traceability.
> Enforces structured outputs from examples and supported schema controls.
> Processes long documents with chunking, parallel work, and multiple passes.
> Generates self-contained interactive HTML to review extracted entities.
> Supports cloud models and local Ollama models through documented providers.

It replaces a hand-built chain of prompting, offset tracking, schema cleanup, and separate result visualization with one documented library workflow.

Apache-2.0 licensed; local Ollama models provide a usable path without a cloud API key, while cloud models require their own credentials.

Github repo: https://t.co/SiwqQZrAu5

[joithan @jothantranston]

@_mattwelter @grok summerize

[joithan @jothantranston]

GitHub work from the terminal: • Review: pull requests • Triage: issues • Delivery: Actions • Automation: scripts A saveable map of where GitHub CLI fits. https://t.co/tA563eJm9Z

[Jun Song @jun_song]

Here is why we must protect @huggingface from being banned:

A lot of people think we can just download models with BitTorrent on PirateBay and call it a day.

But HF isn’t just a weight repository—it plays a massive role in detecting malware in models through safetensor inspections.

This shields us from models embedded with malware, and embedding hidden malicious code inside weights or prompt templates is way easier than people think.

We went through a ton of issues just like this on clawhub earlier this year.

[Neeraj @neerajjj6785]

When you ask Claude a question

And instead of answering, he decides to write 5000 lines of code and burn all your limits

[Mike Bradley @MikeBradleyAI]

“GLM 5.2 saves the day and protects a US corporation from a dangerous closed source US AI lab. In response, US AI lab suggests banning GLM 5.2.”

[Planet Of Memes @PlanetOfMemes]

The bad guys have evolved.

[Hugging Models @HuggingModels]

OpenAI:

“We’re launching an investigation to find whoever hacked Hugging Face.”

opens internal logs

“…”

“Guys.”