![\"\"](\"https:\/\/sdtimes.com\/wp-content\/uploads\/2026\/01\/RepoHeader_01-490x198.png\")
<\/p>\nGitHub Copilot SDK now in technical preview<\/b><\/h4>\n
The SDK<\/a> permits builders to embed agentic capabilities into their purposes utilizing the identical execution loop utilized by the GitHub Copilot CLI. The SDK repository consists of setup directions, starter examples, and SDK references for the entire supported languages.<\/p>\n GitHub recommends beginning by defining a single process, equivalent to updating information or working a command, and letting Copilot plan and execute steps whereas the appliance provides domain-specific instruments and constraints.<\/p>\n The structure<\/a> is Anthropic\u2019s imaginative and prescient for Claude\u2019s values and conduct. The primary sections on this up to date model embody specs associated to helpfulness, ethics, security, nature, and tips for how one can deal with particular points, like medical recommendation or cybersecurity requests.<\/p>\n \u201cThe structure is an important a part of our mannequin coaching course of, and its content material immediately shapes Claude\u2019s conduct. Coaching fashions is a troublesome process, and Claude\u2019s outputs may not all the time adhere to the structure\u2019s beliefs. However we predict that the best way the brand new structure is written\u2014with a radical clarification of our intentions and the explanations behind them\u2014makes it extra more likely to domesticate good values throughout coaching,\u201d Anthropic wrote.<\/p>\n The corporate introduced that it is going to be utilizing age prediction expertise on ChatGPT client plans to find out if a person is underneath 18.<\/p>\n \u201cAge prediction builds on protections already in place. Teenagers who inform us they’re underneath 18 after they join mechanically obtain extra safeguards to scale back publicity to delicate or doubtlessly dangerous content material. This additionally allows us to deal with adults like adults and use our instruments in the best way that they need, inside the bounds of security,\u201d OpenAI wrote in a put up<\/a>.<\/p>\n GitLab has made its Duo Agent Platform typically obtainable<\/a>, offering growth groups with agentic AI automation that has entry to a company\u2019s full context, requirements, and guardrails.<\/p>\n The GA launch consists of Agentic Chat, offering context-aware help all through the GitLab platform. Agentic Chat builds on the beforehand launched Duo Chat, and brings in context from points, merge requests, pipelines, safety findings, and extra, and might carry out actions on a developer\u2019s behalf.<\/p>\n For instance, within the Net UI, Agentic Chat can create points, epics, merge requests, and spotlight key findings and create actionable steering based mostly on organizational context. Moreover, within the IDE, it might generate code, configurations, and infrastructure-as-code, in addition to repair bugs, generate texts, and produce documentation.<\/p>\n Different methods Agentic Chat can be utilized are serving to builders perceive, configure, or troubleshoot CI\/CD pipelines or create new ones, and on the safety entrance, it might clarify vulnerabilities, assist with challenge prioritization, and advocate fixes.<\/p>\n Codenotary is including new capabilities<\/a> to its SBOM.sh service, which offers free evaluation of software program payments of supplies (SBOMs).<\/p>\n In line with the corporate, the updates have been made in consideration of AI purposes, and the instrument now treats datasets as software program provide chain artifacts.<\/p>\n \u201cConventional SBOM instruments have been constructed for an earlier period \u2013 focusing totally on supply code to enhance visibility into the software program provide chain,\u201d stated Moshe Bar, CEO and co-founder of Codenotary. \u201cSafety groups are swimming in SBOMs, however they\u2019re not getting the actionable readability they want \u2014 particularly as AI transforms software program with AI purposes are constructed on datasets that are solely ignored by conventional SBOMs.\u201d<\/p>\nAnthropic drafts new structure for Claude fashions<\/b><\/h4>\n
OpenAI provides age prediction to ChatGPT<\/b><\/h4>\n
GitLab\u2019s Duo Agent Platform is now typically obtainable<\/b><\/h4>\n
Codenotary updates its free SBOM scanning instrument with capabilities that higher assist AI apps<\/b><\/h4>\n
Testlio launches new AI-powered QA evaluation resolution<\/b><\/h4>\n