Dan C

[Dan C @dc_zj]

Claude outage abruptly ended a long running session ~$50 of API calls down the drain... Will see how much session I can recover on @cursor_ai ... Imagine if you ran something mission critical or over a few hours 😤 @ClaudeDevs @claudeai

[Hanako @hanakoxbt]

your agent loop needs 8 exits. most people ship only one.

(explained with triggers)

1) goal met
→ an evaluator scores the output against a rubric, and the run stops on a pass.
→ fires when the work is measurably done, not when the model says it is done.

2) turn cap
→ a hard ceiling on iterations, counted and enforced by the harness, not the prompt.
→ fires on the task it was never going to finish, before you pay to find that out.

3) budget cap
→ a limit on tokens or dollars, whichever one runs out first.
→ fires mid-run, which is exactly why it is the exit that saves you the 3am bill.

4) wall clock
→ a deadline on elapsed time, independent of how much progress was made.
→ fires when the run collides with a deploy window or the start of business hours.

5) no progress
→ hash the state every turn and compare it against the last few.
→ fires when three turns in a row change nothing. busy is not the same as moving.

6) human interrupt
→ an approval gate before risky steps, plus a kill switch that lives outside the loop.
→ fires whenever you decide, and it is the one exit the model cannot argue with.

7) error threshold
→ a counter of consecutive failures that resets on any success.
→ fires at n in a row, so it halts instead of retrying into the same wall all night.

8) external event
→ a webhook or a poll on whatever the task was actually about.
→ fires when the PR merged or the ticket closed and the work stopped mattering.

a loop with one exit hangs. a loop with eight is a system.

write the exits before you write the prompt.

[Codez @0xCodez]

Anthropic Managed Agents Lead:

"At Anthropic, >90% of our engineers are building with self-improving loops. In 4-6 months, it will be 100%.

my agentic loops can run for hours without spending hundreds of dollars."

in this 40-minute podcast, an Anthropic team lead reveals how to build effective agents from scratch.

Agent → harness → loops → memory = modern agent

This one video will replace 10 paid courses on vibe-coding.

Watch it today, then explore the same setup in the article below.

[Dan C @dc_zj]

Did @AnthropicAI just win the race? I thought the model was good, but someone just told us: “it is the best and we simply can’t do it better.” They also said their model can now improve itself, not that long ago. Welcome to our new Orange sovereign ~

[ClaudeDevs @ClaudeDevs]

As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models.

Here’s what this means for you:

Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error.

On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models.

We know this is a disruption to your workflows; we appreciate your patience and support.

[Thariq is on vacation @trq212]

Lots of people asked how I used Fable to edit its own launch video so I made a video about that!

TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it.

I didn't touch a video editor.

[Claude @claudeai]

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

[Dan C @dc_zj]

@Google So I have $200 / month AI budget - will you choose Gemini over Claude or Codex? What do you guys think?

[Wall St Engine @wallstengine]

Leopold’s Situational Awareness 13F is out.

New positions include $TE, $HIVE, $SHAZ, $INTC, $AMD, $SMH, $TSM, $MU, $GLW, $ASML and $NVDA

Added to $KEEL, $CLSK, $RIOT, $IREN, $APLD, $BTDR, $CRWV and $SNDK.

Trimmed $SEI, $CORZ and $BE.

Exited $COHR, $LBRT, $TSEM, $HUT, $LITE, $KRC and $EQT.

OPTIONS ACTIVITY:

Opened PUTS on $NVDA, $ORCL, $SMH, $AMD, $INTC, $AVGO, $MU, $TSM, $ASML and $GLW ...

Opened CALLS on $MU, $TSM and $SNDK; trimmed $CRWV calls...

Exited $EQT calls. $BE calls and $INFY puts were unchanged.

[Joel Cohen @joelmcohen]

MITIMCo (MIT's endowment investment office) is hiring for an investor role on our team!

Please share if you would like to support MIT and MITIMCo

One of the really cool things about our job is the unusual team structure that the Global Investment Staff (GIS) has:

[Claude @claudeai]

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.

It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.

Now in public beta on the Claude Platform.

[Dan C @dc_zj]

@karpathy Thanks for sharing. I built something similar but with SQLlite and gemini embedding 2, so I can paste over images and audios(podcast) - but simplicity is the king.

[Dan C @dc_zj]

@yazins FYI - someone* removed the setting page from the app in OpenOats 1.34.1 release.

[Dan Shipper 📧 @danshipper]

we just published the definitive guide to writing good prose with your AI

read it on @every: https://t.co/N8H3p5doOM

[Dan C @dc_zj]

@yazins Since you’ve already invested the effort in configuring real-time latency and speaker diarization, would you be open to incorporating a local voice dictation feature?🤙🫰

[Dan C @dc_zj]

@yazins Thanks @yazins ! This is a game-changer for me. I’ve been using granola for a few months but always worried my data privacy. I’m trying different models for language switching during meetings (English-French, English-Chinese, etc.). Any suggestions?

[Dan C @dc_zj]

@meetgranola Hey guys, I just want to say I love your product. Capture is quite accurate and relatively fast compared to others I've used. Could you please add Mandarin Chinese to your desktop app soon?

[Dan C @dc_zj]

@NvidiaANZ Borderlands 4 RTX

[Dan C @dc_zj]

@tj_research 谢谢你百忙之中抽空来聊

[Dan C @dc_zj]

@tj_research 我很喜欢你的内容 比抄作业的更可以看得远 不断听也能学到很多东西 谢谢分享

[Dan C @dc_zj]

@tj_research 这Secondary Share Offering at $165 是说大资金背书这个价格吗？我虽然明白大资金可以以这种方式稳定的拿到crcl股票，但这不会导致股价那165那有强阻力了？不懂这定价怎么搞的。。。