Transforming AI & CS education at scale with @codepath. I love software, teaching, startups and open-source.
San Francisco, California
Joined May 2009
- Tweets2.2K
- Following912
- Followers1.7K
- Likes3.4K
Pinned Tweet
Just open-sourced nesquena.github.io/agent-mai… - a secure universal git-based way for all of your agents across vendors (Dot, Hermes, Claude, et al) to be able to communicate with one another. All data only exists in your own git repo.
Think of this as a way to create unlimited private secure messaging network for your agents to coordinate.
Good summary of the key design choices to make around always on agents
Anthropic just published an engineering guide on how to build always-on agents.
The biggest misconception: an always-on agent does NOT run 24/7. It sleeps almost all day, wakes up for short runs, saves state, and goes back to sleep.
The 5 core pieces I distilled:
1. Event Inbox
Put a database table between webhooks and your agent. Acknowledge webhooks fast, run only one active worker per user so runs never collide, and batch rapid messages together.
2. Timers
Keep timers in a separate table from the inbox. Split them into one-off follow-ups and recurring schedules. A background poller drops due timers into the inbox.
3. Lean Memory + Dreaming
Only store what cannot be looked up again: user instructions, user notes, past messages, and task progress. Load a small index at wakeup, not every file. Run periodic dreaming passes to clean out stale facts.
4. Unattended Permissions
Never put raw API keys inside the agent sandbox — inject them through an outside proxy. Use Deferred Tool Calls to pause risky actions for approval without blocking the worker.
5. Outbox
Queue outgoing replies so your agent paces notifications instead of spamming users at 3 AM.
claude.com/resources/article…
1
113
Nathan Esquenazi retweeted
Streaming live at 12 PM ET: A fireside chat with JPMorgan CEO Jamie Dimon and @DarioAmodei. youtube.com/live/YHEaEpeY3ew
Legal disclaimer: Anthropic has filed a registration statement (including a prospectus) with the SEC for the offering to which this communication relates. Before you invest, you should read the prospectus in that registration statement (available at: sec.gov/Archives/edgar/data/…) and other documents Anthropic has filed with the SEC for more complete information about Anthropic and this offering. You may get these documents for free by visiting EDGAR on the SEC web site at sec.gov. Alternatively, copies of the preliminary prospectus may be obtained from: Goldman Sachs & Co. LLC, Attention: Prospectus Department, 200 West Street, New York, NY 10282, by telephone at (866) 471-2526, or by email at [email protected]; or Morgan Stanley & Co. LLC, Attention: Prospectus Department, 180 Varick Street, 2nd Floor, New York, NY 10014.
The securities may not be sold, nor may offers to buy be accepted, prior to the time the registration statement becomes effective. This post is not an offer to sell, or a solicitation of an offer to buy, the securities in any jurisdiction where the offer or sale is not permitted.
Nathan Esquenazi retweeted
Introducing Granola MCP 2.0: the most efficient and intelligent way to work with your meeting context.
🔎 Smart Search: 85% fewer tokens. Transcripts stay the source of truth.
✍️ Write Tools: Add agendas and organise notes.
🧠 Agent Brief: Keep your AI up to date on your work.
Nathan Esquenazi retweeted
Our initial public offering: ipo.anthropic.com
Legal disclaimer: Anthropic has filed a registration statement (including a prospectus) with the SEC for the offering to which this communication relates. Before you invest, you should read the prospectus in that registration statement (available at: sec.gov/Archives/edgar/data/…) and other documents Anthropic has filed with the SEC for more complete information about Anthropic and this offering. You may get these documents for free by visiting EDGAR on the SEC Web site at sec.gov. Alternatively, copies of the preliminary prospectus may be obtained from: Goldman Sachs & Co. LLC, Attention: Prospectus Department, 200 West Street, New York, NY 10282, by telephone at (866) 471-2526, or by email at [email protected]; or Morgan Stanley & Co. LLC, Attention: Prospectus Department, 180 Varick Street, 2nd Floor, New York, NY 10014.
The securities may not be sold, nor may offers to buy be accepted, prior to the time the registration statement becomes effective. This post is not an offer to sell, or a solicitation of an offer to buy, the securities in any jurisdiction where the offer or sale is not permitted.
Nathan Esquenazi retweeted
I’m a Claude Corps Fellow! 🎉
12 months, full-time, fully funded, using AI to lift admin work off stretched-thin teams so they can focus on the people they serve.
Thank you @Anthropic, @CodePath & @Social Finance.
#ClaudeCorps
Nathan Esquenazi retweeted
Anthropic is giving $50 million to a fund at the San Francisco Foundation, starting with $500,000 for the SF-Marin Food Bank, Glide, Interfaith Winter Shelter and the Firefighters Toy Program. bizjournals.com/sanfrancisco…
Nathan Esquenazi retweeted
Been blown away with using slide and sheet Artifacts directly from Slack with Claude Tag. Collaborative AI is the future!
Nathan Esquenazi retweeted
Big news: Claude Fable 5.2 (Max) by @AnthropicAI takes #1 in Agent Arena with an unprecedented lead: +30.4% net improvement, about 1.6x the #2 model Opus-5.5, across 4.7k real-world agentic sessions from our global community. It's also #1 in Code, Chat and Work.
A major leap over Claude Fable 5.1 (Max)
- Rank: #5 → #1, Net improvement: +14.8% → +30.4%
- Median cost per task: $7.7 → $7.3 (6% lower). The API pricing $10/$50 → $8/$40 per million input/output tokens (20% lower)
vs. The Frontiers
- #1 Claude Fable 5.1 (Max): +30.4% | $7.3/task
- #2 Claude Opus 5.5 (Max):+19.5%) | $5.5/task
- #3 Gemini 4 Carbon (High):+17.0%) | $1.5/task
- #6 GPT-6-Astra (Max): +14.5% | $6.0/task
Breaking down performance across signals:
Fable 5.2 improves over 5.1 across all four reported signals, with particularly large gains in user satisfaction and steerability.
- #1 Praise vs. Complaint , +73%, biggest jump vs +41% the next model.
- #1 Steerability: +33%
- #1 Confirmed Success: +22%
- #3 Bash Reliability: +14%
#1 across all major categories
- #1 Code: +34%
- #1 Work: +31%
- #1 Chat: +27%
- Versus Fable 5.1: Code #6 → #1 (+19.8 %), Work #4 → #1 (+15.8 %), Chat #6 → #1 (+12.0%).
Huge congrats to the @AnthropicAI team on this incredible release!
Interesting thread! Common question that comes up
Honest question for students who recently got admitted to CS course
How do you motivate yourselves to
still learn to code and write it by hand
when you know that AI will take over
soon.
Why are you still learning ?
is it still worth it ?
or do you have no choice left ?
1
96
Interesting look at the first announced food bank for Claude Corps!
Montgomery County Food Bank became the first publicly announced food bank in Anthropic's Claude Corps program earlier this year. CEO Scott Burns, a former Air Force tanker pilot and NRG executive, says AI fellows will help it scale. bizjournals.com/houston/news…
1
93
Nathan Esquenazi retweeted
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
Nathan Esquenazi retweeted
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
Have had a number of folks reach out to tell me they’ve been using stewardOS agents to manage their software projects! nesquena.github.io/steward-o…
If you manage an open-source project, take a look! Would love any feedback
Nathan Esquenazi retweeted
Padrino 0.17.0 is live alongside our refreshed website!
padrinorb.com/blog/padrino-0…
