Product Hunt ·
telemetry.dev
Observability for AI agents
Home / Browse
All stories
Browse every indexed public story, including items outside the main categories.
8397 public stories
量子位 ·
刚刚，Gemini 4 Carbon全面超越Opus 5.5！首发Token半价
能连肝数日修Bug，免疫提示词注入
GitHub Issues ·
With a `TimeoutPolicy` on a node and `step_timeout` on the graph it runs, resuming after a sibling's failure makes that graph return before its `Send` fan-out ran
Public issue #9484 in langchain-ai/langgraph. The source issue contains the full report and discussion.
OpenAI ·
Credit Saison achieves 954% ROI in a ChatGPT Enterprise pilot
Credit Saison’s ChatGPT Enterprise pilot delivered 954% ROI. See how leaders and employees helped turn the results into companywide adoption.
Hugging Face ·
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready
Public article from Hugging Face. Open the source to read the full record.
Hugging Face ·
Welcome Le Chonk: Mistral Large 4 on Hugging Face
Public article from Hugging Face. Open the source to read the full record.
Product Hunt ·
Flatbread
Share the whole agent run, not a screenshot
Simon Willison ·
Quoting Ted Sanders
In general, LLM performance is incredibly multidimensional. There's no guarantee of a fixed ordering where the model that is best at math is also the model that's best at jokes. Despite that complexity, much of the variation in performance is explained by just a single variable: model size. In general, models that are bigger will (a) be more performant / reliable, (b) cost more per token, and (c) have better recall of esoteric facts. As you note, our models are ordered: Luna < Terra < Sol
TechCrunch ·
Upwind raises $400M after walking away from Datadog acquisition offer
The cloud security startup raised a Series C at a $3.8B valuation, instead of selling itself for the same price.
GitHub Issues ·
Image preprocessing ~20% slower on Linux since v5.18.0: in-place normalize (#48897) causes extra page faults
Public issue #50100 in huggingface/transformers. The source issue contains the full report and discussion.
GitHub Issues ·
ClapFeatureExtractor forces is_longer=True in fusion mode when every clip is ≤10 s
Public issue #50097 in huggingface/transformers. The source issue contains the full report and discussion.
TechCrunch ·
Apple’s touchscreen MacBook Pro pushes laptop pricing to a new extreme
Prepare to cough up around $14,549 if you want the new touchscreen MacBook Pro to have every upgrade.
Product Hunt ·
AssemblyAI
text-to-speech built for voice agents
Hacker News ·
Our AI Agent Executed the Same Successful SQL Query 254 Times
Submitted by armcat. Hacker News recorded 4 points and 0 comments as of Oct 29, 2026 (UTC).
Product Hunt ·
AutoShelf 2.6
Automate any folder on your Mac with if-this-then-that rules
GitHub Issues ·
[serge] integration failure triage - 2026-10-28
Public issue #50096 in huggingface/transformers. The source issue contains the full report and discussion.
Hacker News ·
When AI goes rogue, its human overseers may be to blame
Submitted by andrewstetsenko. Hacker News recorded 4 points and 1 comments as of Oct 29, 2026 (UTC).
TechCrunch ·
Microsoft just shared Azure’s actual revenue in dollars: $33.2 billion
Microsoft has never disclosed Azure's quarterly revenue in dollars. But for the first time, we can see just how close it is getting to besting the biggest competitor in the market, AWS.
GitHub Issues ·
apply_chat_template ignores return_tensors=None for processors that default to tensors (e.g. Pixtral)
Public issue #50094 in huggingface/transformers. The source issue contains the full report and discussion.
TechCrunch ·
Google expands AI Search ads globally as core ad growth slows
The announcement came alongside parent company Alphabet's third-quarter earnings report, which saw revenue grow 25% year over year to $127.6 billion.
Hacker News ·
AI agent skills for better second-hand decisions
Submitted by mjovanc. Hacker News recorded 2 points and 0 comments as of Oct 29, 2026 (UTC).
TechCrunch ·
Microsoft recorded $10 billion in revenue from OpenAI
Microsoft said it made $10 billion in revenue from commercial arrangements with OpenAI, including revenue-sharing payments, in the quarter ending September 30. It underscores the still-enormous financial dependency of the partnership.
SEC EDGAR ·
8-K - TECHPRECISION CORP (0001328792) (Filer)
Filed: 2026-10-28 AccNo: 0001104659-26-119706 Size: 258 KB Item 1.01: Entry into a Material Definitive Agreement Item 9.01: Financial Statements and Exhibits
SEC EDGAR ·
8-K - Cactus, Inc. (0001699136) (Filer)
Filed: 2026-10-28 AccNo: 0001628280-26-067952 Size: 553 KB Item 2.02: Results of Operations and Financial Condition Item 9.01: Financial Statements and Exhibits
SEC EDGAR ·
8-K - S&T BANCORP INC (0000719220) (Filer)
Filed: 2026-10-28 AccNo: 0000719220-26-000117 Size: 391 KB Item 8.01: Other Events Item 9.01: Financial Statements and Exhibits
SEC EDGAR ·
8-K - CNL Strategic Capital, LLC (0001684682) (Filer)
Filed: 2026-10-28 AccNo: 0001999371-26-023789 Size: 193 KB Item 5.07: Submission of Matters to a Vote of Security Holders
GitHub Issues ·
JsonPlusSerializer: pydantic RootModel state loses its type on checkpoint round trip and breaks interrupt/resume
Public issue #9480 in langchain-ai/langgraph. The source issue contains the full report and discussion.
SEC EDGAR ·
8-K - Star Equity Holdings, Inc. (0001210708) (Filer)
Filed: 2026-10-28 AccNo: 0001210708-26-000090 Size: 1 MB Item 1.01: Entry into a Material Definitive Agreement Item 3.02: Unregistered Sales of Equity Securities Item 7.01: Regulation FD Disclosure Item 9.01: Financial Statements and Exhibits
SEC EDGAR ·
8-K - First Breach, Inc. (0001892704) (Filer)
Filed: 2026-10-28 AccNo: 0001493152-26-049110 Size: 411 KB Item 1.02: Termination of a Material Definitive Agreement Item 7.01: Regulation FD Disclosure Item 9.01: Financial Statements and Exhibits