Partial day — headline is the last complete day (2026-10-13).
twitter
tracked since 2026-10-11T21:55:46.572374+00:00
conclusion
Measured mentions per day
day (UTC)
mentions
2026-10-04
12
2026-10-05
7
2026-10-06
6
2026-10-07
9
2026-10-08
5
2026-10-09
4
2026-10-10
6
2026-10-11
4
2026-10-12
8
2026-10-13
2
2026-10-14
0
derived from
python
word-boundary match over title + text, query='timeline' · window
2026-10-04 → 2026-10-15
· 63 matching posts
evidenceShowing 20 newest of 63
•
twitterShubhamInTech1dneutral
MakeMyTrip is a ~$4 billion travel company.
I use Myra, its AI travel assistant, to code Python for me! https://t.co/FT9nG0zIKwMakeMyTrip is a ~$4 billion travel company.
I use Myra, its AI travel assistant, to code Python for me! https://t.co/FT9nG0zIKw
🐍📺 Using the Terminal on macOS — https://t.co/Np0nz4IqBx
#python https://t.co/GmOmsulrQa🐍📺 Using the Terminal on macOS — https://t.co/Np0nz4IqBx
#python https://t.co/GmOmsulrQa
REA (Reverse Engineer Anything) is the MOST dangerous MCP for traders
i am literally SHOCKED...
REA (Reverse Engineer Anything) could crack apart any trading system from scratch & inspect its source code along with its binaries for completely FREE
i wrote a 6-page research paper on using REA + Opus 5.5 to reverse-en…REA (Reverse Engineer Anything) is the MOST dangerous MCP for traders
i am literally SHOCKED...
REA (Reverse Engineer Anything) could crack apart any trading system from scratch & inspect its source code along with its binaries for completely FREE
i wrote a 6-page research paper on using REA + Opus 5.5 to reverse-engineer trading mechanics & build your own trading agents in RUST
here is how you do it:
1. the REA workflow investigates application behavior, traces code paths, maps dependencies and reconstructs how trading systems operate
2. the source-code and binary analysis layer examines functions, recovers program structure, and traces implementation details in authorized targets
3. the behavioral analysis engine studies order submissions, cancellations, market-data updates and execution events to infer trading mechanics
4. the Opus 5.5 research agent turns findings into Python models, trading bots and testable strategy hypotheses
5. the backtesting engine evaluates strategies against historical data, fees, slippage, out-of-sample periods, and predefined validation criteria
6. the autonomous research loop logs experiments, investigates failures, monitors performance, and refines strategies under explicit risk limits
the full research framework is in my article below:
I have 32 tabs open in Chrome right now.
Research, work, that one tweet I'm "getting back to," 3 different ChatGPT sessions, and maybe 8 I don't remember opening.
So I built a Chrome extension that organizes all of them for me.
It's called SnapTab, and it runs on SubQ Snap, a new decision model from Subquadratic @su…I have 32 tabs open in Chrome right now.
Research, work, that one tweet I'm "getting back to," 3 different ChatGPT sessions, and maybe 8 I don't remember opening.
So I built a Chrome extension that organizes all of them for me.
It's called SnapTab, and it runs on SubQ Snap, a new decision model from Subquadratic @subquadratic that handles small, structured calls faster and cheaper than an LLM. I got early access, and this was the first thing I wanted to build with it.
Open the extension and it shows you every tab, every group you've made, and every duplicate quietly eating your memory.
Then you hit Analyze.
That one click sends your tabs to a local Python server running Snap. The model reads every title and URL and figures out what each tab actually is. Research. Dev. Entertainment. Work.
Hit Organize, and Chrome snaps them into clean groups instantly.
I didn't send any of this to an LLM. Snap has a 384k context window, 12x larger than other decision models, so it can hold your entire browser session in one shot and still cost pennies.
Video below.
Hiring at Voyfai!
We are looking for 2 people to join our Engineering and Product team in Berlin:
👉 Senior AI Product Engineer
👉 Senior Product Manager
At Voyfai, we build AI for freight forwarders, the people who move goods around the world.
Who we're looking for:
🔹 AI Product Engineer: you have shipped LLM f…Hiring at Voyfai!
We are looking for 2 people to join our Engineering and Product team in Berlin:
👉 Senior AI Product Engineer
👉 Senior Product Manager
At Voyfai, we build AI for freight forwarders, the people who move goods around the world.
Who we're looking for:
🔹 AI Product Engineer: you have shipped LLM features in production and you have experience working with Python and TypeScript.
🔹 Product Manager: you have owned products end to end, ideally in B2B software, and you use AI tools every day to move from idea to prototype in days
M
>The Rust compiler is Rust
>Deno is Rust
>uv (Python package manager) is Rust
>Ruff (Python linter) is Rust
>ripgrep is Rust
>Polars is Rust
>Firecracker (AWS microVMs) is Rust
>Bevy game engine is Rust
>Zed editor is Rust
>Tauri is Rust
>Meilisearch is Rust
>Turborepo is Rust
>Oxc (JavaScript tools) is Rust
>Vaultward…>The Rust compiler is Rust
>Deno is Rust
>uv (Python package manager) is Rust
>Ruff (Python linter) is Rust
>ripgrep is Rust
>Polars is Rust
>Firecracker (AWS microVMs) is Rust
>Bevy game engine is Rust
>Zed editor is Rust
>Tauri is Rust
>Meilisearch is Rust
>Turborepo is Rust
>Oxc (JavaScript tools) is Rust
>Vaultwarden is Rust
>Tock (embedded OS) is Rust
>Ruffle (Flash emulator) is Rust
>Yazi (terminal file manager) is Rust
>Lapce editor is Rust
-still, you are not convinced to learn Rust
Want to create beautiful stacked bar charts using Python?
With Pygal, you can visualize data trends and compare multiple categories across different years with just a few lines of code.
In this example, we compare the popularity of Python, Java, and JavaScript from 2022 to 2026 using a stacked bar chart.
What you wi…Want to create beautiful stacked bar charts using Python?
With Pygal, you can visualize data trends and compare multiple categories across different years with just a few lines of code.
In this example, we compare the popularity of Python, Java, and JavaScript from 2022 to 2026 using a stacked bar chart.
What you will learn:
Create stacked bar charts with Pygal
Add custom titles and axis labels
Visualize multiple datasets in one chart
Display SVG charts directly in Jupyter Notebook
I’m releasing NeuroRoute 1024, an update to my old Neuroute project. A project written in C11 that combines a deterministic routing engine with a multi-language development toolchain.
The repository contains two independent components.
NeuroRoute Core is a lightweight routing and spatial-matching engine built around:…I’m releasing NeuroRoute 1024, an update to my old Neuroute project. A project written in C11 that combines a deterministic routing engine with a multi-language development toolchain.
The repository contains two independent components.
NeuroRoute Core is a lightweight routing and spatial-matching engine built around:
* A graph of up to 1,024 nodes with weighted connections, activation thresholds, and deterministic route selection.
* Exact 1,024-bit spatial matching using Hamming distance across 16 × 64-bit words.
* Synaptic activity counters, fallback routing, and atomic synchronization for shared state.
* A standalone C library that can be integrated into other applications.
NeuroRoute DevTools is a command-line development environment supporting eight programming languages:
C, C++, Python, Rust, JavaScript, Go, Zig, and Java.
It provides a consistent interface for detecting projects, identifying installed toolchains, initializing projects, building, running, testing, and cleaning.
Instead of introducing another compiler or translating code between languages, DevTools works directly with the existing toolchains, including GCC, Clang, Cargo, Node.js, npm, Go, Zig, and the Java JDK.
Project detection examines source files and manifests, prioritizes explicit project configurations, and reports ambiguous results rather than guessing.
Process execution uses POSIX APIs without passing commands through a shell. Missing toolchains and unsupported project configurations are reported explicitly.
Both components are independently buildable and maintained in a single repository, with their own source code, tests, and documentation.
The release includes Linux validation using GCC and Clang, static analysis, AddressSanitizer and UndefinedBehaviorSanitizer testing, source-integrity checks, and architecture documentation. Rust and Zig integration is implemented but was not exercised with installed toolchains in the local validation environment.
The objective is to prov
I have unlocked a new superpower with Claude. Not only have I solved solitaire, but more importantly, I’ve discovered that pythonista on iOS can build ui’s. That means I can conjure apps in real time on my phone using Claude and python. What should I build? https://t.co/6dFkf70gWwI have unlocked a new superpower with Claude. Not only have I solved solitaire, but more importantly, I’ve discovered that pythonista on iOS can build ui’s. That means I can conjure apps in real time on my phone using Claude and python. What should I build? https://t.co/6dFkf70gWw
this 20-year-old reportedly made $37,250 in a single month creating youtube content while barely touching editing software.
he built an autonomous content factory.
claude is the brain.
premiere pro is the body.
and the workflow handles most of the production.
here’s how it works:
→ claude researches high-cpm niches…this 20-year-old reportedly made $37,250 in a single month creating youtube content while barely touching editing software.
he built an autonomous content factory.
claude is the brain.
premiere pro is the body.
and the workflow handles most of the production.
here’s how it works:
→ claude researches high-cpm niches
→ writes the scripts
→ uses python to trigger voiceovers
→ generates visuals
→ assembles the videos
→ sends everything to premiere pro for the final render
the system can run around the clock while he focuses on other things.
during his first month, one channel reportedly pulled hundreds of thousands of shorts views.
but the client-work model is even more interesting:
→ $400 per video
→ roughly 15 minutes of ai processing
→ $400 in revenue per completed video
at 20 videos a week, that’s $8,000 in potential weekly revenue before expenses, assuming every video sells at that rate.
his role?
provide the idea, build the system, and let ai handle much of the production, from the opening line to the final render.
the real opportunity isn’t just generating videos faster.
it’s building a workflow that can produce them consistently without doing every step manually.
bookmark this for later.
🐍❓ Python Sets Quiz — Test your understanding of Python sets #python https://t.co/UPPCbt69Pf🐍❓ Python Sets Quiz — Test your understanding of Python sets #python https://t.co/UPPCbt69Pf
🐍 Packaging Your Code — The Hitchhiker's Guide to #Python
https://t.co/iFnsnhs6kH🐍 Packaging Your Code — The Hitchhiker's Guide to #Python
https://t.co/iFnsnhs6kH
10 000 décisions SEO te coûtent 42 centimes maintenant
J'ai monté le MEILLEUR agent de maillage interne avec Jev AI
(il décide où pointe chaque lien de ton site pour quelques centimes)
Je te donne le setup complet gratuitement
Comment ça marche :
→ tu lui donnes ton sitemap (ça tourne sur n8n, Make ou un simple sc…10 000 décisions SEO te coûtent 42 centimes maintenant
J'ai monté le MEILLEUR agent de maillage interne avec Jev AI
(il décide où pointe chaque lien de ton site pour quelques centimes)
Je te donne le setup complet gratuitement
Comment ça marche :
→ tu lui donnes ton sitemap (ça tourne sur n8n, Make ou un simple script Python)
→ pour chaque page, il choisit la meilleure cible de lien parmi 255 pages max
→ il te rend son choix avec un score de confiance entre 0 et 1
Il lit le contenu de chaque page, garde en auto les liens au-dessus de ton seuil et t'envoie le reste à vérifier
1. Follow
2. Like + signet
3. Commente "jev"
(guide dispo en français et en anglais)
🚨 Someone just built an AI that turns a 13-minute walkthrough video into a complete 3D map, streamed live, at 20 frames per second.
Not a one-shot photo-to-3D converter. A model that watches a video as it plays and continuously reconstructs the 3D world — stable over sequences longer than 10,000 frames.
It's called L…🚨 Someone just built an AI that turns a 13-minute walkthrough video into a complete 3D map, streamed live, at 20 frames per second.
Not a one-shot photo-to-3D converter. A model that watches a video as it plays and continuously reconstructs the 3D world — stable over sequences longer than 10,000 frames.
It's called LingBot-Map. ECCV 2026 Best Paper Award Candidate. 17,800 stars. And the engineering problem it solves is the one that's kept real-time 3D reconstruction stuck in research labs for years.
Here's the gap it closes.
Traditional 3D reconstruction — the kind used in robotics, AR, and autonomous navigation — works by iterative optimization. Feed in a whole video, let an algorithm grind through it for minutes or hours, get a point cloud back. That's fine for offline processing. It's useless if a robot needs to understand where it is right now, while it's still moving.
Streaming reconstruction has always traded accuracy for speed, or speed for sequence length — long videos caused drift, where the reconstructed camera position slowly diverges from reality the longer the sequence runs.
LingBot-Map's Geometric Context Transformer fixes both simultaneously.
Here's the architecture trick that makes 10,000+ frame sequences stable.
Three components working together: anchor context for coordinate grounding, a pose-reference window for dense geometric cues, and trajectory memory for long-range drift correction. The model doesn't just process the current frame — it maintains a running memory of where it's been, continuously correcting itself against that memory so errors don't compound over a 13-minute walkthrough.
Paired with paged KV cache attention via FlashInfer, the same technique that makes long-context LLM inference efficient — applied here to 3D geometry instead of text.
Here's what 20 FPS at 518×378 resolution actually means in practice.
Point a camera at a space. The model builds the 3D map as you walk through it, in real time, without the pose drifti
PDFs often hide valuable business data inside reports, invoices, and contracts.
In this guide, @manishmshiva shows you how to automatically extract PDF data with Python.
You'll extract text and tables, handle scanned PDFs with OCR, clean the data, and export the results to Excel or CSV.
https://t.co/MqIraFgBn3PDFs often hide valuable business data inside reports, invoices, and contracts.
In this guide, @manishmshiva shows you how to automatically extract PDF data with Python.
You'll extract text and tables, handle scanned PDFs with OCR, clean the data, and export the results to Excel or CSV.
https://t.co/MqIraFgBn3