OpenAI announced ChatGPT Work and the author of this piece documents how it works after iterating since July 9.
ChatGPT Work is available only to subscribers paying at least $20/month (free and $8/month tiers do not have access).
The article claims Work adds cloud execution with internet-capable code, a headless Chrome browser, persistent shared filesystem access across sessions, and capabilities like publishing ChatGPT Sites and running sub-agent sessions.
OpenAI notified SpaceX that it plans to wind down its contract supplying OpenAI models to Cursor after citing concerns that SpaceX may not use the models under OpenAI’s terms of service.
AI agents are shifting retrieval needs so that evidence delivery must be correct and timely for systems that investigate, reason, and act on users’ behalf. The article highlights that when retrieval is commoditized, competitive advantage shifts to decisioning, i.e., deciding what an agent should see and in what order before it acts. Engineers will therefore focus on end-to-end retrieval engineering workflows (hybrid retrieval, real-time signals, ranking, inference, and experimentation) rather than only embeddings or vector search.
Agent demos can look reliable until real inputs trigger missing records, tool errors, policy changes, or capability limits that reveal the system is not production-ready. The article’s example billing trace includes a 13.4s run that used 2,180 tokens and cost $0.04, illustrating how a harness logs and gates work around the model. Production deployments change by treating the model as only one component and adding tool contracts, permissions, deliberate context, traces, and failure-focused tests so wrong calls are contained and diagnosable.
AppGacha turns a plain-language wish into a real desktop app with utilities, widgets, games, and personal tools that run locally. The launch page lists 53 followers. As a result, users can generate portable apps and organize them in their own desktop workspace.
Every AI story that matters,
in your inbox by 8am.
TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the
day in two minutes. Follow companies and topics for alerts, or get the
briefing in Slack. Free, no spam, unsubscribe anytime.
Reading TLDRocket needs no cookies, and the readership counts we rely on come from
our own cookieless analytics. Google Analytics is the exception: it sets cookies and
reports to Google, so it stays switched off until you allow it. You can change your
mind any time from “Cookie settings” in the footer.
Strictly necessary
Session security and form protection (tldrocket-session,
XSRF-TOKEN, 2 hours). The site cannot work without them,
so they need no consent.
Always on
Google Analytics 4 (_ga,
_ga_<id>, up to 2 years). Measures which
stories and sections readers use. Google acts as a third-party processor and may
store the data outside the EU. No advertising, no profiling, no data sold.
