Charly Wargnier ♨️

Deep in Agents, LLMs and automation · Open source at ♥ · Sharing AI gems daily to help you work smarter · Ex-data scientist @Snowflake | @Streamlit ·

[Charly Wargnier ♨️ @DataChaz]

accurate af

[Charly Wargnier ♨️ @DataChaz]

accurate af

[Charly Wargnier ♨️ @DataChaz]

plausible twist by @TTX66XTT

[Charly Wargnier ♨️ @DataChaz]

accurate af

[Charly Wargnier ♨️ @DataChaz]

@TTX66XTT plausible actually.

[Charly Wargnier ♨️ @DataChaz]

@victor_vibing @treg_ai I'm also wondering about the reverse 😁

@treg_ai is OSS and pretty flexible, so why not?

[Charly Wargnier ♨️ @DataChaz]

AN OPEN-SOURCE RECRUITER. ABOUT $0.19 PER CANDIDATE.

Give Claude Code or Codex a job description.

@treg_ai finds candidates, ranks them against your criteria and looks up personal emails and mobiles where available.

It checks career history, code, talks and posts, with sources behind the matches.

No monthly recruiter seat. Pay as you go.

The $0.19 figure comes from treg’s recorded run.

FREE and open-source.

Repo in 🧵↓

[Charly Wargnier ♨️ @DataChaz]

@aksenHQ @treg_ai That is an excellent point. @treg_ai do you have the answer?

[Charly Wargnier ♨️ @DataChaz]

Repo → https://t.co/F4AptoCxek

Shoutout to @treg_ai for building this and making it open-source for the community.

Don't forget to drop a ★!

[Charly Wargnier ♨️ @DataChaz]

@alexmashrabov @JensenHuang That’s what I love to see. Well done!👏

[Alex 🧩 Scaling Video GenAI @alexmashrabov]

@jensenhuang and NVIDIA just invested in Higgsfield

We turn competition at the foundation layer into compounding advantage for our customers. Every advance at the frontier expands what Higgsfield can deliver

The moat is ownership of demand, and we clearly own one.

[Charly Wargnier ♨️ @DataChaz]

@melvindvivas @bot @larsencc this doesn't seem to be working for me:

https://t.co/XB7mBRU8Wr

[Charly Wargnier ♨️ @DataChaz]

@bot summarize this

[Charly Wargnier ♨️ @DataChaz]

@bot summarize this

[Charly Wargnier ♨️ @DataChaz]

YOUR AGENT CAN RUN ALL NIGHT. YOUR BUDGET WILL NOT.

43% of enterprises struggle to prove AI's business value, while 27% cannot even track token spend across systems.

@StackletIO just launched Token Custodian to close that gap.

An agent stuck in a retry loop can balloon its context window on every turn.

By the time a monthly billing alert arrives, the money is already gone...

Built by the team behind CNCF Cloud Custodian, Stacklet already governs $10B+ in enterprise cloud spend, cutting cloud and AI bills by up to 50% and governance overhead by 80%.

Token Custodian brings real-time enforcement to LLM tokens:

> attribute tokens and agent runs to teams, projects, apps, and cost centers across providers
> cap agent steps, runtime, and context growth per run
> pause runaway loops automatically and alert owners in Slack
> switch routine requests to cheaper models at 80% budget usage, with approvals for frontier model exceptions

FinOps sets budgets in the UI.

Platform teams manage policies as code in Git across coding assistants and customer-facing agents.

The results?

savings 6x faster, with flat subscription pricing instead of a percentage of spend 🔥

now in early preview ahead of the October 27 Token Governance Summit (event link in 🧵↓)

Explore it here → https://t.co/EMvL6lNPz4

[Charly Wargnier ♨️ @DataChaz]

HELL YEAH. GrokBot needs this.

Let us pick the right model for the right task

[Machina @EXM7777]

this is literally all i need, please make it happen @leerob

[Charly Wargnier ♨️ @DataChaz]

@melvindvivas @elonmusk deserved! 👏👏👏

[Charly Wargnier ♨️ @DataChaz]

@antonpme nice!

where do you live?

[Charly Wargnier ♨️ @DataChaz]

This is what autumn looks like where I live.

This is Gourette, in the French Pyrenees.

Beautiful photos by Nicolle Perrin.

[Charly Wargnier ♨️ @DataChaz]

@DanielGPT2022 too many sheeps in there already.

[Charly Wargnier ♨️ @DataChaz]

@DanielGPT2022 Sheeps are looting apparently

[Charly Wargnier ♨️ @DataChaz]

@crystalwizard ignore reviews?

it depends :)