there’s two experimental modes for gpt we are currently testing. You can enable strict mode that nudges the model to keep working; and you can switch to codex app server as harness.
TOOLS
-
Kindle Notes to Notion: Better Retrieval Than Sticky Notes
By
–
I’m not organised enough to manage sticky notes – I find retrieval difficult. I know it comes naturally to some people. My Kindle notes go to a Notion folder – so I can search them easily.
-
InsForge: Open-Source Backend Solution for AI Coding Agents
By
–
AI agents suck at backend.
— Akshay 🚀 (@akshay_pachaar) 11 avril 2026
They ship beautiful frontends in seconds, but completely fall apart the moment you ask for a database, auth, or storage.
InsForge is an open-source solution, built natively for AI coding agents and editors. It exposes backend primitives like… pic.twitter.com/S5YvYSUkAHAI agents suck at backend. They ship beautiful frontends in seconds, but completely fall apart the moment you ask for a database, auth, or storage. InsForge is an open-source solution, built natively for AI coding agents and editors. It exposes backend primitives like databases, auth, storage, and functions through a semantic layer that agents can understand, reason about, and operate end-to-end. It works with any agent you already use, whether that is Cursor, Claude Code, Codex, OpenClaw, or Hermes. 100% open source. GitHub repo: github.com/InsForge/InsForge (don't forget to star 🌟)
→ View original post on X — @akshay_pachaar, 2026-04-11 12:40 UTC
-
Accelerating LLM Fine-tuning with Open Source Libraries
By
–
Fine-tuning massive LLMs used to be painfully slow, but not anymore! 4 open source libraries that accelerate fine-tuning of Large Language Models 1. Unsloth AI • Fine-tune models like Qwen3, Llama 4, and Gemma 3 up to 2× faster with 70% less VRAM
• Uses optimized Triton -
Agent Skills Repo Adds Engineering Capabilities to AI Coding Agents
By
–
AI coding agents are fast but reckless. They skip specs, tests, and security. Google engineer just open-sourced a fix. Agent Skills is a free repo that brings 19 engineering skills and 7 slash commands to any AI coding agent. It works by encoding what senior engineers
-
Free library of 10,000+ prompts for Claude, ChatGPT, Gemini
By
–
Te regalo esta web con más de 10,000 prompts con MILES de opciones para Claude, ChatGPT y Nano Banana (Gemini)
— Nico (@nicos_ai) 11 avril 2026
Divididos por usos, profesiones y más
100% gratis aquí abajo ⬇️ pic.twitter.com/E0q146uK3vI’m gifting you this website with over 10,000 prompts featuring THOUSANDS of options for Claude, ChatGPT, and Nano Banana (Gemini) Divided by uses, professions, and more 100% free right below
-
Vibe Coded Email App with Dial-Up Modem Works First Try
By
–
✉️ Vibe coded a POP3 and SMTP text-based email app for https://t.co/rltvxoEavc that uses the dial-up modem to check and send emails and it worked on the first try
— @levelsio (@levelsio) 11 avril 2026
It's internal email only so web@pieter.com to web@pieter.com and the same email box as on https://t.co/RRYOCWqRQq… https://t.co/JwzsqzGTkv pic.twitter.com/FMI2FwaGEpVibe coded a POP3 and SMTP text-based email app for http://
os.pieter.com that uses the dial-up modem to check and send emails and it worked on the first try It's internal email only so web@pieter.com to web@pieter.com and the same email box as on http://
pieter.com -
/ultraplan: Build implementation plans in cloud while coding locally
By
–
🚨 Claude Code users, your workflow is about to get significantly faster.
— Charly Wargnier (@DataChaz) 11 avril 2026
The new `/ultraplan` is incredibly mighty 🔥
Instead of locking up your terminal, Claude now lets you build and refine your implementation plans in the cloud while you keep working locally.
Here is… pic.twitter.com/REQkMPmvz3🚨 Claude Code users, your workflow is about to get significantly faster. The new `/ultraplan` is incredibly mighty 🔥 Instead of locking up your terminal, Claude now lets you build and refine your implementation plans in the cloud while you keep working locally. Here is exactly how to use it: → Type /ultraplan followed by your prompt in your local terminal → Keep coding while Claude researches your codebase in the cloud → Open the generated session link in your browser to leave inline feedback → Click to approve the plan and teleport it back to your terminal The finalized plan is injected right back into your local session, ready to be built ↓
-
Scaling Drug Discovery Through Unified Biomedical Workflows
By
–
Drug discovery is where this becomes strategic. Instead of manually stitching databases: → ADMET evaluation → Drug-likeness scoring → Repurposing signals via disease pathway and drug-target mapping → Multi-omics integration → Regulatory network inference and regulon activity scoring 100+ biomedical tools and thousands of recent papers unified into reproducible workflows. This is how you scale insight across labs and teams.
→ View original post on X — @ronald_vanloon, 2026-04-11 08:30 UTC
-
AI-Powered Drug Discovery Pipeline: From Sentence to Full Analysis
By
–
What if your next drug discovery pipeline started with one sentence, not 6 months of scripting?
— Ronald van Loon (@Ronald_vanLoon) 11 avril 2026
In this latest deep dive with @scispace, I saw a shift that feels bigger than incremental AI gains.
Upload single-cell data and get clustered cell types, UMAPs, marker annotations,… pic.twitter.com/91MIdlMKUwWhat if your next drug discovery pipeline started with one sentence, not 6 months of scripting? In this latest deep dive with @scispace, I saw a shift that feels bigger than incremental AI gains. Upload single-cell data and get clustered cell types, UMAPs, marker annotations, causal gene rankings, and ADMET analysis in one structured flow. This changes the operating model. Here’s the breakdown…
→ View original post on X — @ronald_vanloon, 2026-04-11 08:30 UTC