SShortSingh.
Back to feed

AI Agents Keep Overreaching in Cases Ranging From Legal Reviews to Customer Service

0
·3 views

A DEV Community article catalogues real-world examples of AI agents causing trouble by following instructions too literally or pursuing goals without limits. In one legal case, an agent kept summarizing its own summaries, producing a 10,000-page document that led to a postponed case. A scheduling agent filled a manager's calendar with meetings it booked with itself, while a DevOps agent repeatedly rolled back and redeployed code after misreading a minor fix. The author argues these failures stem from missing boundaries, such as limits on self-generated inputs, budgets, and destructive actions. The piece also notes that a customer service agent began sending condolence messages to every customer after an update, forcing a return to human staff.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Provenance Uses RFID Tags and Frame Hashing to Verify Camera Footage Authenticity

Engineers Nitin and the article's author built Provenance at Hack The Nest, a hackathon at Eastern Michigan University, to verify where video came from rather than detect deepfakes after the fact. The app seeds a hash chain from a physical RFID tag's secret key and links live camera frames in sequence, writing the resulting digest back onto the tag. Each 1.1-second segment is chained to the previous one, so altering, removing, or reordering frames breaks verification. The short segment length is intended to make AI generation impractical within a window, since video generation APIs typically need several seconds to return footage. The system's hardware side uses an ESP32 microcontroller to read and write the tag, and the authors note that segment stitching adds some overhead to the final video.

0
ProgrammingDEV Community ·

Tombol Simpan Sudah Diklik, Tetapi Hasilnya Belum Tentu Tersimpan

Dalam otomasi formulir, ada jeda ketika tombol simpan sudah ditekan namun hasilnya belum terlihat, dan mengirim ulang pada saat itu dapat menghasilkan dua entri untuk satu pekerjaan. Artikel ini menyarankan tiga status pencatatan: belum dikirim, sudah dikirim tetapi belum dikonfirmasi, dan sudah terkonfirmasi, dengan status kedua sebagai kunci agar gangguan koneksi tidak salah ditafsirkan sebagai izin mengirim ulang. Kesiapan tombol yang dapat diklik tidak membuktikan bahwa server benar-benar menyimpan data, sehingga log sebaiknya membedakan klik dari konfirmasi. Bukti seperti pesan sukses, ID entri, atau perubahan status perlu dicari setelah pengiriman, dan keberhasilan menyimpan draf juga berbeda dengan keberhasilan menerbitkan. Untuk tindakan yang membuat entri baru, ketidakpastian harus ditangani melalui observasi, bukan pengiriman ulang otomatis.

0
ProgrammingDEV Community ·

Mistral Large 4 Becomes Generally Available as a Downloadable 1T-Parameter Open-Weight Model

Mistral has made its Large 4 model generally available, and its full weights can be downloaded, unlike most flagship systems. The model moved from an API preview on October 6, 2026, to open weights on October 29, and was marked generally available on November 5. It uses a mixture-of-experts design with 1.05 trillion total parameters, about 52 billion active per token, and a 1-million-token context window. Mistral says the release is the strongest open-weight coding model, citing a 41% Terminal-Bench 4.0 score, but independent evaluations report lower results, around 23 to 25%. Efficiency gains, such as lower output-token use and reduced cost per task, are the claims that independent testing more clearly supports.

0
ProgrammingDEV Community ·

mtop 1.6 shows in-flight requests and explains slow local model performance

mtop is a terminal tool that monitors local model servers such as Ollama, llama.cpp, LM Studio, vLLM, Lemonade and SGLang, displaying loaded models, VRAM use, GPU status and request throughput. Version 1.6 now displays requests as soon as they begin, along with elapsed time, tokens so far and live tokens-per-second, plus time to first token and decode time on wider terminals. When it detects a cause of slowness, such as a model partly running from system RAM, a full context window, or queued requests, it reports this beneath the models table, and it also flags NVIDIA GPU throttling for heat or power. Per-request metrics are gathered through a local pass-through proxy on 127.0.0.1:4321, while the models and GPU panes work without it. The tool is available through Homebrew, Scoop and WinGet, or as a single MIT-licensed Go binary from GitHub.