Pop-Up Thingie

War Ensemble BBS
  • Home
  • Forum
  • Files
  • Log in

  1. Forum
  2. DOVE-Net
  3. Tech Talk
  • ChatGPT writing styles ✍️ , ByteDance AI 📱, how agents test 👨‍💻

    From TLDR@VERT to All on Tue Sep 8 10:39:33 2026
    OpenAI appears to be implementing a new feature that helps ChatGPT
    write in users' voices by referencing examples from their connected apps ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌  ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ ‌ 


    Sign Up [1] |Advertise [2]|View Online [3]

    TLDR

    TOGETHER WITH [Lightfield] [4]

    TLDR 2026-09-08

    EVERYONE IS LYING TO YOUR CRM (SPONSOR) [4]

    Not on purpose! But stages are always optimistic and close dates go
    stale. People are busy...  

    Lightfield [5] is the agentic CRM that builds the record from the
    conversations themselves, capturing every email, call, and meeting as
    it happens. So the questions your CRM could never answer, this one
    can.

    Ask "WHY DO WE KEEP LOSING TO COMPETITOR X, WITH QUOTES FROM THE
    ACTUAL CALLS." Get real answers and see the evidence. [6]

    5,000+ companies signed up in the ten months since launch. Book a demo
    [7]

    📱

    BIG TECH & STARTUPS

    CHATGPT MAY SOON LEARN YOUR WRITING STYLE FROM YOUR SLACK OR GMAIL (2
    MINUTE READ) [8]

    OpenAI appears to be implementing a new feature that helps ChatGPT
    write in users' voices by referencing examples from their connected
    apps. Some users have had the feature for weeks, but the company has
    yet to officially announce the tool. OpenAI often tests new ideas with
    select users ahead of launch. The article includes a screenshot of the
    feature interface.

    BYTEDANCE JOINS AI ELITE IN RACE TO PERFECT WORLD MODELS (5 MINUTE
    READ) [9]

    ByteDance is preparing to launch a real-time spatial video AI model.
    The model will be able to create interactive virtual worlds. It will
    also be able to generate virtual worlds that respond to Pico VR
    headset users' voices and movements. ByteDance is planning a launch as
    soon as next month.

    🚀

    SCIENCE & FUTURISTIC TECHNOLOGY

    EARLY DATA INDICATES AN AI-GENERATED DRUG COULD SLOW AGING (2 MINUTE
    READ) [10]

    Rentosertib is a drug created with the assistance of AI. The AI
    originally indicated that the drug could help treat patients suffering
    from a chronic lung disease, but data from clinical trials show it
    could also slow the aging process. The drug reduced the biological
    markers of age as measured by six 'aging clocks', a different kind of
    AI technology designed to predict a person's morbidity and mortality.
    While the drug shows promise, it is still years away from regulatory
    approval, even for use in sick patients.

    XPENG STARTS IRON HUMANOID ROBOT PRODUCTION AS TESLA OPTIMUS STALLS
    (5 MINUTE READ) [11]

    XPeng has started production for its IRON robot. Its production line
    runs with more than 80% of its core processes automated. The company's
    robot went viral last year as its walk was so smooth that people
    accused XPeng of hiding a person in a costume. XPeng is targeting mass production by the end of the year.

    💻

    PROGRAMMING, DESIGN & DATA SCIENCE

    YOUR AI AGENTS NEED GUARDRAILS AND BOUNDARIES (SPONSOR) [12]

    What are your AI agents doing? What do they have access to? Teleport
    gives you answers and helps you set boundaries to contain and control
    them. Monitor and audit agent behavior to better understand the risks
    related to AI in your environment. 

    Join Teleport September 17th to learn more. [13]

    HOW WELL DO AGENTS USE TEST/VERIFICATION TECHNIQUES? (68 MINUTE READ)
    [14]

    It's easier than ever to hit a particular quality bar by having
    coding agents use effective test techniques. However, software quality
    seems to be getting worse. This indicates that whatever defaults
    developers are using might not work very well. This study tests
    whether simple instructions to agents to use particular techniques or
    libraries improve implementation correctness. It found that agents
    tend to either just write the tests they would normally write, but
    inside a framework for a different type of test technique, or they'll
    use a technique superficially but not really do the things that get
    the value out of the technique.

    THE YEAR FINDING AND EXPLOITING BUGS BECAME CHEAP, AND WHAT TO DO
    ABOUT IT (13 MINUTE READ) [15]

    Over the next few years, offensive capability will become abundant.
    More people will be able to inspect every valuable project and exploit vulnerabilities. Handling critical bugs in a timely manner will become
    the most challenging and important task for defenders. Having good
    security infrastructure and integration will be a must. AI-assisted formalization will lower some of the cost, but writing the right
    specification and connecting proofs to production code will remain
    challenging.

    🎁

    MISCELLANEOUS

    PRODUCT MANAGER, APPLIED AI AT TLDR ($200K BASE + $60K BONUS, FULLY
    REMOTE) [16]

    TLDR is hiring its first PM to help build the agent-first operating
    layer used across the company. We're looking for a builder who has
    shipped real products/systems with LLMs. Click here to learn more
    [16].

    DE-BRAINROT VACATIONS (6 MINUTE READ) [17]

    The monotony of work can make it hard to keep a clear head. Spend
    your vacations doing something different for your brain. Slow down and
    double down on new habits you want to grow. Spend time in nature,
    socialize, play games, engage with hobbies, and you'll notice you
    might start being less intellectually lazy during your day-to-day
    activities.

    FOUR QUESTIONS ABOUT AGI (28 MINUTE READ) [18]

    Artificial General Intelligence (AGI), as the term is commonly used,
    points to nothing really tangible or concrete and points us at the
    wrong thing. Recent announcements about AGI are just companies saying
    they've nearly arrived at a destination they defined themselves.
    Instead of trying to define AGI, the industry should focus on making a
    long series of specific things reliable enough to trust, and let the destination take care of itself.

    ⚡

    QUICK LINKS

    WHAT WE CAN LEARN FROM CLAUDE'S FABLE 5.1 SYSTEM PROMPT (14 MINUTE
    READ) [19]

    Comparing how system prompts develop over time demonstrates how model
    quirks and product design are moving targets.

    SIMPLE IS NOT SMALL (11 MINUTE READ) [20]

    Writing simple programs requires a good mental model of the program
    as well as good taste.

    ONE FLOOR UP (5 MINUTE READ) [21]

    Someone working outside an experiment can still be affected by what
    happens inside it.

    TESLA CYBERCAB SPECS: SUPERMANIFOLD V3, NO RARE EARTH MAGNETS, & MORE
    (5 MINUTE READ) [22]

    This article details the Tesla Cybercab's dimensions, mechanical
    packaging, and custom thermal hardware.

    HUAWEI LAUNCHES MATE XT 2 TRI-FOLD TWO DAYS BEFORE APPLE'S FOLDABLE
    IPHONE (5 MINUTE READ) [23]

    Huawei's new tri-folding phone, the Mate XT 2, opens to a 10.2-inch
    display.

    RUFF, MYPY, PYTEST, AND THEN WHAT? (7 MINUTE READ) [24]

    Code that is well-structured is easier to maintain and also easier
    for agents to work with.

    Love TLDR? Tell your friends and get rewards!

    Share your referral link below with friends to get free TLDR swag!

    https://refer.tldr.tech/66662a80/ [25]

    Track your referrals here. [26]

    Want to advertise in TLDR? 📰

    If your company is interested in reaching an audience of tech
    executives, decision-makers and engineers, you may want to ADVERTISE
    WITH US [27].

    Want to work at TLDR? 💼

    APPLY HERE [28], CREATE YOUR OWN ROLE [29] or send a friend's resume
    to [email protected] and get $1k if we hire them! TLDR is one of INC.'S
    BEST BOOTSTRAPPED BUSINESSES [30] of 2025.

    If you have any comments or feedback, just respond to this email!

    Thanks for reading,
    Dan Ni [31] & Stephen Flanders [32]

    Manage your subscriptions [33] to our other newsletters on tech,
    startups, and programming. Or if TLDR isn't for you, please
    unsubscribe [34].



    Links:
    ------
    [1] https://tldr.tech/signup?utm_source=tldr
    [2] https://advertise.tldr.tech/?utm_source=tldr&utm_medium=newsletter&utm_campaign=advertisetopnav
    [3] https://a.tldrnewsletter.com/web-version?ep=1&lc=265280dc-d4e0-11f0-a661-1b9fa34a893d&p=58201de0-ab5e-11f1-86f4-d919bb260171&pt=campaign&t=1788863973&s=51102440b7406022be4f079f82aade40c81bc20b15daacc0a61f3fadb5232657
    [4] https://lightfield.app/clp/default-2?utm_source=newsletter&utm_medium=paid&utm_campaign=tldr&utm_content=primary_9-8-2026_header_everyone_lying_crm
    [5] https://lightfield.app/clp/default-2?utm_source=newsletter&utm_medium=paid&utm_campaign=tldr&utm_content=primary_9-8-2026_Body_lightfield
    [6] https://lightfield.app/clp/default-2?utm_source=newsletter&utm_medium=paid&utm_campaign=tldr&utm_content=primary_9-8-2026_Body_evidence
    [7] https://lightfield.app/clp/default-2?utm_source=TLDR&utm_medium=newsletter&utm_campaign=2026-09-08_Primary_Lightfield&utm_content=cta_book_demo
    [8] https://www.pcmag.com/news/chatgpt-may-soon-learn-your-writing-style-from-your-slack-or-gmail?utm_source=tldrnewsletter
    [9] https://links.tldrnewsletter.com/SCLA9O
    [10] https://links.tldrnewsletter.com/CQRbJy
    [11] https://electrek.co/2026/09/07/xpeng-iron-humanoid-robot-production-line/?utm_source=tldrnewsletter
    [12] https://fandf.co/46lGOEt?utm_source=tldrnewsletter
    [13] https://fandf.co/46lGOEt
    [14] https://danluu.com/agentic-testing/?utm_source=tldrnewsletter
    [15] https://blog.zksecurity.xyz/posts/the-year-finding-bugs-became-cheap/?utm_source=tldrnewsletter
    [16] https://jobs.ashbyhq.com/tldr.tech/897f4391-66ab-44ca-a8eb-65dd9809200d?utm_source=tldr
    [17] https://devz.cl/posts/i-spent-my-vacations-de-brainrotting/?utm_source=tldrnewsletter
    [18] https://voiceinthemachine.com/2026/09/07/four-questions-about-agi/?utm_source=tldrnewsletter
    [19] https://www.dbreunig.com/2026/09/07/what-we-can-learn-from-claude-s-fable-5-1-system-prompt.html?utm_source=tldrnewsletter
    [20] https://jyn.dev/simple-is-not-the-same-as-small/?utm_source=tldrnewsletter [21] https://www.distributedthoughts.org/2026-09-07-one-floor-up/?utm_source=tldrnewsletter
    [22] https://www.notateslaapp.com/news/4657/tesla-cybercab-specs-supermanifold-v3-no-rare-earth-magnets-more?utm_source=tldrnewsletter
    [23] https://thenextweb.com/news/huawei-mate-xt-2-foldable-apple-xiaomi?utm_source=tldrnewsletter
    [24] https://codescan.dev/blog/ruff-mypy-pytest-and-then-what?utm_source=tldrnewsletter
    [25] https://refer.tldr.tech/66662a80/
    [26] https://hub.sparklp.co/sub_e87ba9c7d7c0/1
    [27] https://advertise.tldr.tech/?utm_source=tldr&utm_medium=newsletter&utm_campaign=advertisecta
    [28] https://jobs.ashbyhq.com/tldr.tech
    [29] https://jobs.ashbyhq.com/tldr.tech/c227b917-a6a4-40ce-8950-d3e165357871 [30] https://www.linkedin.com/feed/update/urn:li:activity:7401699691039830016/ [31] https://twitter.com/tldrdan
    [32] https://twitter.com/SteveFlanders22
    [33] https://tldr.tech/tech/manage?email=tldrnewsletter%40synchro.net
    [34] https://a.tldrnewsletter.com/unsubscribe?ep=1&l=cfa2d55a-b7be-11e8-a3c9-06b79b628af2&lc=265280dc-d4e0-11f0-a661-1b9fa34a893d&p=58201de0-ab5e-11f1-86f4-d919bb260171&pt=campaign&pv=5&spa=1788861661&t=1788863973&s=5b6e60724f3e92b0362a686470c3472411c60eea33c6c9139b903c1127babac0

    ---
    ■ Synchronet ■ Vertrauen ■ Home of Synchronet ■ [vert/cvs/bbs].synchro.net
  • Who's Online

  • Recent Visitors

    • Arisance
      Thu Sep 10 06:50:43 2026
      from Oshkosh, Wi via Telnet
    • Noozle
      Thu Sep 10 06:40:11 2026
      from Noozle City via Telnet
    • Arisance
      Wed Sep 9 07:35:21 2026
      from Oshkosh, Wi via Telnet
    • Noozle
      Wed Sep 9 06:41:39 2026
      from Noozle City via Telnet
  • System Info

    Sysop: DaiTengu
    Location: Appleton, WI
    Users: 1,136
    Nodes: 10 (0 / 10)
    Uptime: 15:51:21
    Calls: 14,591
    Calls today: 2
    Files: 186,473
    D/L today: 10,305 files
    (3,185M bytes)
    Messages: 2,577,504

© War Ensemble BBS, 2026