Keep up the good work and do let us know if there’s other ways Codex/ OpenAI can help with your work!
GENERATIVE AI
-
Databricks Unveils Lakebase Operational Database for AI Agents
By
–
Databricks AI Days are underway, bringing together 15,000+ data and AI leaders to see how modern teams are building and shipping intelligent apps. This year, the spotlight is on Lakebase: a new category of operational database built for the age of agents, where storage and
-
Using AI for specification processing
By
–
Je pense que c'est très bien, c'est ce que je fais parfois pour faire mes specs et les filer à l'IA
-
Building Twitter Clone in 44 Minutes for $4 with Claude
By
–
Twitter started 20 years ago. In 2022 it was acquired for $44B. Today I build a clone of it in 44 minutes for $4 in Claude credits.
-
LM Studio Adds Qwen 3.5 Models to Available Options
By
–
@lmstudio you should get the Qwen 3.5 models listed on https://
lmstudio.ai/models! -
Interactive AI Future Scenarios Dashboard by Bob Gourley
By
–
Are you tired of just listening to others tell you what AI will bring us in the future? The loudest voices are the doomers, who seem to think our only choice is to all die sooner or, if we do things their way, maybe we can all die later. What if there were a way for you to run your own scenarios based on your own inputs? I built a dashboard that will let you do just that. For me, every scenario I run says the future is going to be bright, but some choices make it brighter than others. But try it yourself and form your own opinions. open.substack.com/pub/bobgou…
→ View original post on X — @bobgourley, 2026-03-21 17:14 UTC
-
French Students Get into Y Combinator with AI Consulting Alternative
By
–
> be us, two French students on a gap year > take 12 hours of train in a single day to make it to a @ycombinator x Paris event last July > hear @t_blom mention the opportunity to rethink the audit and consulting model > spend months doing traditional consulting to understand exactly where it breaks > publish two benchmarks seen by 12M+ people to better understand frontier models outside of maths and code > spend weeks designing an AI-native alternative to consulting > build the first end-to-end version > apply to YC > get into YC to build a new way for companies to solve business problems Can’t wait for what comes next ! Raphaël Dabadie (YC P26) (@RaphaelDabadie) x.com/i/article/203529374253… — https://nitter.net/RaphaelDabadie/status/2035401835507323018#m
→ View original post on X — @flashtweet, 2026-03-21 17:07 UTC
-
AI Progress Measured by Intelligence Sharpe Ratio
By
–
A good measure of progress in AI is the intelligence Sharpe ratio, a system's average intelligence across tasks divided by its standard deviation. By this measure, current AIs are still very weak because their variance is so high.
-
Web chat planning with Claude AI and coding assistants workflow
By
–
Planning in the web chat is great. The coding assistant is always way too impatient to get started. Getting a md out of http://
claude.ai and taking it to the agent works really well a lot of the time -
Claude Unshipped RAG for Search: Agentic Approach Better
By
–
We did RAG early on then unshipped it for a number of reasons: privacy, security, reliability, index staleness. Overall, we found that agentic search gave better results with fewer tradeoffs. If you prefer RAG, we recommend an MCP like Souregraph, or just ask Claude to build a