Working in Claude-Code or Codex-CLI and nearing full context usage? Compaction loses information, so here's a tool I built to let you continue the work without compaction github.com/pchalasani/c... #claude-code #codex #cli #agents

Set up a colored context progress bar for Claude Code: Instructions here: github.com/pchalasani/c...

Fun new game: prompt gymnastics to get past Sora’s content filter 😂 Here’s one result:

With the Claude Sonnet 4.5 release there are interesting new context management and memory features in the API — www.anthropic.com/news/context... Anyone know if these are used in Claude-Code?

Used Claude Code to build a simple tool tmux-cli that lets CC puppet your terminal -- i.e. interact with CLIs expecting user input -- useful to let CC autonomously run debuggers, test CLI/UI scripts, spawn other Claudes (fully visible unlike black-box sub-agents) github.com/pchalasani/c...

🤯 I was asked internally to summarize @thursdai_pod in 1 slide and just noticed, that just after 2 years of the live shows, 1.5 years of podcast releases and almost 100 episodes (this week is #99!) we have just crossed... 100,000 downloads on Sub**ack 🔥

“Her” is here. A voice-chat so realistic, I’m left speechless. www.sesame.com/research/cro...

The work is mysterious and important: lumon-industries.com

Thanks to a Kagi subscription I haven’t seen a sponsored search ad in a really long time — so long I can’t even remember what those look like 🤣 It’s 2025 and I’m shocked how many still put up with ad surveillance. It’s high time to neuter the business models of Mega-Corps founded on this.

uv is great for python packaging. One of several benefits: You can publish your lib to PyPi so people can run specific scripts from anywhere with zero installs/venv/repo-cloning using uvx --from lib script You just need to add a [project.scripts] section with paths to the scripts

QwQ-32B-Preview from Qwen is the best "o1-like" LLM today. You can run it remotely via glhf.chat super-fast endpoint. Langroid lets you easily use it -- it gets the "Sally question" right, after a LOT of thinking 🤔 (images below) Langroid tour: langroid.github.io/langroid/tut...

llama3.3-70b is a seriously impressive model. Langroid lets you easily try it via groq's insanely fast endpoint - just set the model name to "groq/llama-3.3-70b-specdec" Langroid: agent-oriented LLM framework from CMU/UW-Madison researchers Quick tour: langroid.github.io/langroid/tut...

✍️ "Hard truths about AI-assisted coding" tips & tricks in my latest article: bit.ly/ai-assisted While AI-Assisted coding can get you 70% of the way there (great for prototypes or MVPs), the final 30% requires significant human intervention for quality and maintainability.

Tomorrow morning at the Simons Institute : Sparks versus embers, can LLMs solve major open mathematical conjectures? (FWIW I agree with everything in the Embers paper, so I guess the debate will be about the conclusions to draw from current evidence!) simons.berkeley.edu/talks/sebast...

This is a fun and highly informative weekly show to watch/hear, to catch up on LLM-related developments. Run by @altryne.bsky.social with commentary by @wolfram.ravenwolf.ai @yampeleg.bsky.social @nisten.bsky.social

A special LLM course focusing on Smol models, the <2B parameters generic models which can run on-device/in-browser

How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledge🦜? In our new preprint, we look at the pretraining data and find evidence against this: Procedural knowledge in pretraining drives LLM reasoning ⚙️🔢 🧵⬇️

I put together all of the Bluesky tools/resources I've collected into a list on my website. There are over 60+ different links now, and I've organized them by category: dame.blog/skeet-tools Enjoy! 🦋

list of project ideas that would be a good fit for @atproto.com github.com/bluesky-soci...

Reverse Thinking Makes LLMs Stronger Reasoners abs: arxiv.org/abs/2411.19865 Train an LLM to be able to generate forward reasoning from question, backward question, and backward reaoning from backward question Shows an average 13.53% improvement over the student model’s zero-shot performance

Starter pack for open-source maintainers in the Python ecosystem! Feel free to share and let me know who I'm missing! go.bsky.app/D2Be5mg

When large language models surpass neuroscientists for prediction of results of experiments nature.com/articles/s41... "which presages a future where LLMs assist humans in making discoveries. Our approach is not neuroscience specific and is transferable to other knowledge-intensive endeavours"

The AT Protocol unlocks exciting possibilities: - Building custom feeds using ML - Creating dashboards for data exploration - Developing custom models for Bluesky To gather @bsky.app resources on @huggingface.bsky.social. I've established a community org 🤗 huggingface.co/bluesky-comm...

one of the nice things about bsky is how easy it is to get data from it via the "atproto" python client. See the image and gist for example code, showing how you can get an author's posts, and get your own "home" timeline. gist: gist.github.com/pchalasani/c...

Write math on 🦋 with UnicodeIt! For example: θ ∈ ℝⁿ or pp̅ → μ⁺μ⁻ Use website or install system-wide in Linux, macOS, or windows www.unicodeit.net (Created several years ago with @svenkreiss.bsky.social)

We've made a starter pack for researchers/organizations working on open-source LLMS. Please let us know if we missed you or if you'd like to be added! go.bsky.app/FELkyDr

Looks like the Discover tab has finally learned what I like, after a day of clicking “show more/less like this”

This is easily the most informative and fun weekly podcast on #LLM related developments!

Qwen2.5-Coder-32B-Instruct is impressive for its weight. For those looking to use it in a remote-hosted "free-for-now" way, glhf.chat are hosting it, with great toks/sec. You can easily use it with Langroid, the agent-oriented LLM library -- here's a quick tour langroid.github.io/langroid/tut...